© 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. 58139
    Prev
    Next
    INDEX
    Explanations

    what can

    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
    nt
    -0.09
    ship
    -0.09
    ç®´
    -0.09
    lah
    -0.09
    ãģ¡ãĤĥãĤĵãģ¨
    -0.08
    loid
    -0.08
    éĢĿ
    -0.08
    li
    -0.08
    ight
    -0.08
    çĦī
    -0.08
    POSITIVE LOGITS
    èĥ½ä½¿
    0.10
    åıĪèĥ½
    0.09
    éļ½
    0.09
    å°Ĭ严
    0.09
    ç¨Ķ
    0.09
    ãģĵãģĿ
    0.09
    åıĪæĺ¯
    0.09
    åıĪæľī
    0.09
    togroup
    0.09
    éĻ¤å¤ķ
    0.09
    Activations Density 0.044%

    No Known Activations