© 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. 127634
    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
    完毕
    -0.09
     Bible
    -0.07
    יפה
    -0.07
     ice
    -0.07
     Evening
    -0.07
    ych
    -0.07
     Coffee
    -0.07
    ENCH
    -0.07
    ายน
    -0.07
     Months
    -0.07
    POSITIVE LOGITS
     distort
    0.09
    נגר
    0.08
     governor
    0.07
     distortion
    0.07
     وب
    0.07
     disproportionately
    0.07
    浪费
    0.07
    Har
    0.07
    "'↵
    0.07
    .attr
    0.07
    Activations Density 0.004%

    No Known Activations