© 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. 19-RESID-POST-AA
    11. 128302
    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_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
    Negative Logits
     доб
    -0.07
    -non
    -0.07
    Provider
    -0.07
    tool
    -0.07
     hết
    -0.06
    עבד
    -0.06
    匿
    -0.06
    _percent
    -0.06
    بذل
    -0.06
    DOB
    -0.06
    POSITIVE LOGITS
    кам
    0.09
     poured
    0.07
     crashed
    0.07
    (meta
    0.07
    jni
    0.07
     Personally
    0.07
    規劃
    0.07
     embedded
    0.07
    视听节目
    0.07
     crashes
    0.07
    Activations Density 0.006%

    No Known Activations