© 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. 3708
    Prev
    Next
    INDEX
    Explanations

    cooking liquid

    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
    emann
    -0.09
    å´Ľèµ·
    -0.09
    åıįæĦŁ
    -0.09
     Powell
    -0.09
    触åıĬ
    -0.09
     yıllık
    -0.09
    inded
    -0.09
    åģ¶
    -0.08
    rij
    -0.08
    ä¸įè´Ł
    -0.08
    POSITIVE LOGITS
    汤
    0.11
    æ¯ı次éĥ½
    0.11
    é£İæĻ¯
    0.11
    湯
    0.10
    åı£æ°´
    0.08
    æķŀ
    0.08
    éģ£
    0.08
    沸
    0.08
    ierge
    0.08
    fra
    0.08
    Activations Density 0.036%

    No Known Activations