© 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. 32210
    Prev
    Next
    INDEX
    Explanations

    multiply, multiplication

    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
    lek
    -0.09
     COPYRIGHT
    -0.09
    upro
    -0.09
    leitung
    -0.09
    .blit
    -0.09
    moz
    -0.08
     targ
    -0.08
    fall
    -0.08
    æ²±
    -0.08
    åĸ§
    -0.08
    POSITIVE LOGITS
    åįģä¸ĩ
    0.11
    rog
    0.10
    /div
    0.10
    hare
    0.10
    å¸Ń
    0.09
    lication
    0.09
    cation
    0.09
    Roger
    0.09
    лан
    0.08
    lying
    0.08
    Activations Density 0.145%

    No Known Activations