© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51199
    Prev
    Next
    INDEX
    Explanations

    BBC shows or series

    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
     pole
    -0.09
    [[
    -0.09
    缮
    -0.09
     eg
    -0.08
    rett
    -0.08
    _
    -0.08
    e
    -0.08
    çģ«çĥ§
    -0.08
    è¡ĮæĶ¿æľºåħ³
    -0.08
    çĶŁæ´»çݯå¢ĥ
    -0.08
    POSITIVE LOGITS
    tre
    0.11
    尺度
    0.10
    <!--[
    0.09
    .dw
    0.09
    hci
    0.09
    åīįæıIJæĺ¯
    0.09
    entifier
    0.09
    RITE
    0.09
    mun
    0.09
    stery
    0.09
    Activations Density 0.034%

    No Known Activations