© 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. 8460
    Prev
    Next
    INDEX
    Explanations

    Benjamin

    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
    .dimensions
    -0.08
    IEnumerator
    -0.07
     Jest
    -0.07
    悻
    -0.07
     DE
    -0.07
     unos
    -0.07
     Nobody
    -0.07
    🕓
    -0.07
    嫖
    -0.07
    animated
    -0.06
    POSITIVE LOGITS
    ]]↵↵
    0.08
     drug
    0.07
    科目
    0.07
    低
    0.07
     PLUS
    0.07
     Clara
    0.07
    ภาษา
    0.07
    模块
    0.07
    OC
    0.06
    /************************************************************************************************
    0.06
    Activations Density 0.007%

    No Known Activations