© 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. 19-RESID-POST-AA
    11. 71080
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    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
    	dst
    -0.08
     �
    -0.07
    モノ
    -0.07
    異
    -0.07
    /Public
    -0.07
    /process
    -0.07
    胃
    -0.07
    識
    -0.06
    (history
    -0.06
    เหมาะ
    -0.06
    POSITIVE LOGITS
    zm
    0.07
    arie
    0.07
     Warn
    0.07
    苦笑
    0.07
     "";
↵
    0.07
    尽头
    0.07
    wahl
    0.07
     "";↵
    0.07
    とに
    0.07
     hardcoded
    0.07
    Activations Density 0.087%

    No Known Activations