© 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. 57741
    Prev
    Next
    INDEX
    Explanations

    Huntington disease or Huntingdon Furnace

    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
    pling
    -0.10
    omatic
    -0.10
    lessly
    -0.09
    ë¥ł
    -0.09
    rum
    -0.09
    rabbit
    -0.09
    up
    -0.09
    culate
    -0.09
    缦
    -0.09
    bones
    -0.08
    POSITIVE LOGITS
    athers
    0.10
    olk
    0.10
    izer
    0.10
    ues
    0.09
    åĨįæĿ¥
    0.09
    task
    0.09
    è¿Ļç¯ĩæĸĩç«ł
    0.09
    sd
    0.09
    athan
    0.09
    TAIL
    0.08
    Activations Density 0.021%

    No Known Activations