© 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. 61934
    Prev
    Next
    INDEX
    Explanations

    associated with

    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
    rock
    -0.11
    iness
    -0.10
    º
    -0.10
    人å¿ĥ
    -0.09
    uer
    -0.09
    est
    -0.09
    aces
    -0.09
    azar
    -0.09
    èĻ±
    -0.09
    ernel
    -0.09
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.09
    -sama
    0.08
    ellan
    0.08
    ymous
    0.08
    ively
    0.08
     trách
    0.08
    -purpose
    0.08
     пл
    0.08
    apos
    0.08
    erdale
    0.08
    Activations Density 0.046%

    No Known Activations