© 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. 11-RESID-POST-AA
    11. 26634
    Prev
    Next
    INDEX
    Explanations

    apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wpływ
    -0.06
    ព
    -0.06
    этому
    -0.06
    一点儿
    -0.06
    狨
    -0.06
     rõ
    -0.06
    買った
    -0.06
    읶
    -0.06
    遭
    -0.06
    趟
    -0.06
    POSITIVE LOGITS
     Skip
    0.07
     Kaepernick
    0.07
     Stretch
    0.07
     בחדר
    0.07
    쎅
    0.06
     ExecutionContext
    0.06
     Cache
    0.06
     verso
    0.06
    arcer
    0.06
    _parm
    0.06
    Activations Density 0.041%

    No Known Activations