© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33250
    Prev
    Next
    INDEX
    Explanations

    Jasper, Casper, Jesper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ľåıĸ
    -0.11
    earch
    -0.09
    orest
    -0.09
    ذر
    -0.09
     dotyczÄħ
    -0.09
    raud
    -0.09
    ãģĺ
    -0.08
    稷
    -0.08
    STER
    -0.08
    åŃľ
    -0.08
    POSITIVE LOGITS
    aic
    0.09
    lain
    0.09
    ãĤĤãģĨ
    0.09
    andal
    0.09
    oy
    0.09
    ifik
    0.09
    ../../../
    0.08
    LING
    0.08
    ending
    0.08
    istic
    0.08
    Activations Density 0.017%

    No Known Activations