© 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. 28311
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    end-of-message delimiters marking the end of a user turn in chat-style transcripts.

    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
    .E
    -0.07
    	t
    -0.07
     yardımc
    -0.07
    =BitConverter
    -0.07
    인
    -0.07
    toJson
    -0.07
    _V
    -0.07
    .Manifest
    -0.06
    템
    -0.06
    彀
    -0.06
    POSITIVE LOGITS
    公务
    0.07
     Memorial
    0.07
    basis
    0.07
    owa
    0.07
     Kunst
    0.07
     warrant
    0.06
    كا
    0.06
     Confirm
    0.06
    Offset
    0.06
     cand
    0.06
    Activations Density 0.128%

    No Known Activations