© 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. 27877
    Prev
    Next
    INDEX
    Explanations

    alcohol transmission kills

    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
    ä»ĸ认为
    -0.09
    缴éĶĢ
    -0.08
    笼
    -0.08
    èij¬
    -0.08
    å°ijåĦ¿
    -0.08
    èİ«è¿ĩäºİ
    -0.08
    åIJĥ
    -0.08
    ãĥ¬ãĤ¹
    -0.08
    为äºĨéģ¿åħį
    -0.08
    åĤį
    -0.08
    POSITIVE LOGITS
    åħ¨æĹ¥
    0.12
    çŁŃ
    0.11
    issent
    0.11
    æĵ¦æĭŃ
    0.11
    cloth
    0.09
    ARS
    0.09
    ILI
    0.09
    èĮĥ
    0.09
    à¸Ħะ
    0.09
    æįIJèµł
    0.09
    Activations Density 0.143%

    No Known Activations