Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 130712
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Commit
    -0.07
     להיכנס
    -0.07
    JNIEnv
    -0.07
     spline
    -0.07
    קלא
    -0.07
    🔉
    -0.07
    �
    -0.07
    によって
    -0.07
     денежн
    -0.07
     Dön
    -0.07
    POSITIVE LOGITS
     Abort
    0.07
    laws
    0.07
    无聊
    0.07
     aligned
    0.07
     Palmer
    0.07
    ]</
    0.07
    )&
    0.07
     Lego
    0.07
     wing
    0.06
     הישרא
    0.06
    Activations Density 0.095%

    No Known Activations