© 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. 7053
    Prev
    Next
    INDEX
    Explanations

    stand-up comedy

    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
    èĮľ
    -0.10
    æĢĿ绪
    -0.09
    çĭ¼
    -0.09
    èĶ¬
    -0.09
    秣
    -0.09
    attle
    -0.09
    ç»´å¥ĩ
    -0.09
    åŀ«
    -0.09
    为ä¸Ģä½ĵ
    -0.08
    屯
    -0.08
    POSITIVE LOGITS
    avn
    0.09
    iras
    0.08
    anye
    0.08
    elas
    0.08
    声
    0.08
    .clientWidth
    0.08
    .arch
    0.08
    éļĨ
    0.08
    isode
    0.08
    iker
    0.08
    Activations Density 0.005%

    No Known Activations