© 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. 34351
    Prev
    Next
    INDEX
    Explanations

    StreamSets Inc., Goldcorp, Enceladus

    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
    HomeAs
    -0.10
    åĴĭ
    -0.09
    æľĭåıĭ们对
    -0.09
     Serg
    -0.09
    _locale
    -0.09
    _INTERRUPT
    -0.09
    _MISC
    -0.09
    èĥĥèĤł
    -0.09
    éªĹ
    -0.08
    å¤©åĽ½
    -0.08
    POSITIVE LOGITS
    å¾Ĥ
    0.09
    åŁºæľ¬åİŁåĪĻ
    0.09
    ìĤ¬ìĿ´
    0.09
    横åIJij
    0.08
    rna
    0.08
    æݪæĸ½
    0.08
    lications
    0.08
    .setProperty
    0.08
    INC
    0.08
    iens
    0.08
    Activations Density 0.002%

    No Known Activations