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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77410
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     mừng
    -0.08
    .getConfig
    -0.07
     Granite
    -0.07
    _named
    -0.07
    _crit
    -0.07
    protein
    -0.06
    _activity
    -0.06
    .'/
    -0.06
    uly
    -0.06
    levels
    -0.06
    POSITIVE LOGITS
    در
    0.07
    sistência
    0.07
    зем
    0.07
    зна
    0.07
    ようになった
    0.07
    ?).
    0.06
    RESULT
    0.06
    -mail
    0.06
    reader
    0.06
    씹
    0.06
    Activations Density 0.037%

    No Known Activations