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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72894
    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
    (suffix
    -0.07
    职业
    -0.07
    �
    -0.07
    _coef
    -0.07
    ティー
    -0.07
    号码
    -0.07
    ㅐ
    -0.07
    ⊹
    -0.07
    /respond
    -0.07
    _typ
    -0.06
    POSITIVE LOGITS
    מדינ
    0.07
     weit
    0.07
    🚨
    0.07
    による
    0.07
    explo
    0.06
    Marker
    0.06
    נקוד
    0.06
     Paran
    0.06
    きます
    0.06
    汶川
    0.06
    Activations Density 0.007%

    No Known Activations