© 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. 38886
    Prev
    Next
    INDEX
    Explanations

    command and commander

    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
    icult
    -0.11
    åħļåĨħ
    -0.11
    weet
    -0.10
    asca
    -0.10
    endra
    -0.09
    yps
    -0.09
    gger
    -0.09
    ä¿İ
    -0.09
    纤
    -0.09
    èħĶ
    -0.09
    POSITIVE LOGITS
    eer
    0.12
    isplay
    0.11
    leine
    0.09
    LINE
    0.09
     Pars
    0.08
    åĵ¡
    0.08
    ingly
    0.08
    Ñģел
    0.08
    vu
    0.08
    nets
    0.08
    Activations Density 0.038%

    No Known Activations