© 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. 9622
    Prev
    Next
    INDEX
    Explanations

    wildlife

    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
    æ´¸
    -0.10
    alte
    -0.10
    ode
    -0.10
    éģĵçIJĨ
    -0.09
    æĮ¥
    -0.09
    好人
    -0.09
    pher
    -0.09
    ToObject
    -0.09
    å¾Īæ·±
    -0.09
    è½²
    -0.09
    POSITIVE LOGITS
    uml
    0.11
    horn
    0.10
    çĽĸ
    0.09
    èľ¥
    0.09
    人士
    0.09
    bane
    0.09
    丰å¯Į
    0.09
    avored
    0.08
    ervers
    0.08
    涣
    0.08
    Activations Density 0.022%

    No Known Activations