© 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. 59385
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    gom
    -0.07
    ṿ
    -0.07
     كانوا
    -0.07
    :@
    -0.07
    的钱
    -0.07
     כל
    -0.07
    很明显
    -0.07
     NOW
    -0.07
     למי
    -0.06
     Ging
    -0.06
    POSITIVE LOGITS
    쥉
    0.08
    esters
    0.07
     Casino
    0.07
    restriction
    0.07
    .rotation
    0.07
    溃疡
    0.07
     EI
    0.07
     Curtis
    0.07
    eteria
    0.07
    的特点
    0.06
    Activations Density 0.034%

    No Known Activations