© 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. 32355
    Prev
    Next
    INDEX
    Explanations

    US patent numbers

    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
    alla
    -0.08
    DX
    -0.08
    belt
    -0.08
     belie
    -0.08
    çļ®éĿ©
    -0.08
    åħĭåĪ¶
    -0.08
     Coron
    -0.07
    综åIJĪä½ĵ
    -0.07
    缩çŁŃ
    -0.07
    çľĩ
    -0.07
    POSITIVE LOGITS
    大佬
    0.09
    cov
    0.09
     cov
    0.09
     Cov
    0.08
     foes
    0.08
    åIJĵå¾Ĺ
    0.08
    éĻ·åħ¥äºĨ
    0.08
    æ··
    0.08
    otor
    0.08
    åįĬå¤ľ
    0.08
    Activations Density 0.052%

    No Known Activations