© 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. 11-RESID-POST-AA
    11. 112342
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crap
    -0.08
    ttp
    -0.07
     fluffy
    -0.07
    _detalle
    -0.07
    桯
    -0.07
    ศาล
    -0.07
    ulous
    -0.07
     decode
    -0.07
    ordo
    -0.07
     dismal
    -0.06
    POSITIVE LOGITS
     collaborators
    0.07
    ។
    0.07
    是一位
    0.07
    	synchronized
    0.07
    Adobe
    0.07
    ++){↵↵
    0.07
    得益
    0.07
    (()=>{↵
    0.07
     porque
    0.06
    出现
    0.06
    Activations Density 0.042%

    No Known Activations