© 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. 126926
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .named
    -0.08
    canonical
    -0.08
    我们也
    -0.07
     reap
    -0.07
    现金流
    -0.07
    맸
    -0.07
    mqtt
    -0.07
    Josh
    -0.07
    edReader
    -0.07
     geographical
    -0.07
    POSITIVE LOGITS
    gü
    0.08
    mute
    0.08
    \Schema
    0.07
     iht
    0.07
    -ins
    0.06
     shown
    0.06
     ли
    0.06
    uctions
    0.06
    ли
    0.06
    十八
    0.06
    Activations Density 0.000%

    No Known Activations