© 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. 30221
    Prev
    Next
    INDEX
    Explanations

    the

    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_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
    סין
    -0.07
     מישהו
    -0.07
    شغل
    -0.07
    $h
    -0.06
    veloper
    -0.06
     khăn
    -0.06
     должна
    -0.06
    .Tool
    -0.06
    ${
    -0.06
    	goto
    -0.06
    POSITIVE LOGITS
    此后
    0.07
     burdens
    0.07
     cw
    0.07
    。↵↵↵↵
    0.07
    .Deep
    0.06
    差别
    0.06
     fid
    0.06
     nearby
    0.06
    替代
    0.06
    内心的
    0.06
    Activations Density 0.339%

    No Known Activations