© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18646
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Negative Logits
    试试
    -0.07
     makeup
    -0.06
    _VLAN
    -0.06
    ⅅ
    -0.06
     למ
    -0.06
    .syntax
    -0.06
    𦈡
    -0.06
    懒
    -0.06
     Submit
    -0.06
     עומ
    -0.06
    POSITIVE LOGITS
     Econom
    0.07
     Quickly
    0.07
    Personal
    0.07
    reated
    0.07
    alternative
    0.07
    几十
    0.07
    operation
    0.07
    	fwrite
    0.07
    apor
    0.07
     organisms
    0.07
    Activations Density 0.016%

    No Known Activations