© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 48054
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    polite meta-conversational acknowledgments—apologies and corrections that admit an error, thank the user, and offer further help.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _i
    -0.08
    虺
    -0.07
    _nil
    -0.07
    .sul
    -0.07
    IMPLIED
    -0.07
    _generate
    -0.07
    _wall
    -0.07
     şiddet
    -0.07
    瑱
    -0.07
     Jens
    -0.07
    POSITIVE LOGITS
     hunts
    0.07
     boosted
    0.07
    杆
    0.07
    中断
    0.06
     piping
    0.06
    Git
    0.06
     Measurement
    0.06
    扒
    0.06
    🐿
    0.06
    博
    0.06
    Activations Density 0.039%

    No Known Activations