© 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. 53065
    Prev
    Next
    INDEX
    Explanations

    waiting lists

    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
    otas
    -0.10
     ÑĤек
    -0.09
    _PROC
    -0.09
    éĢ¼
    -0.09
    çģµæĦŁ
    -0.09
    èĪIJ
    -0.08
     arrests
    -0.08
    é»Ħéĩij
    -0.08
    umbing
    -0.08
    byn
    -0.08
    POSITIVE LOGITS
    æ®Ĩ
    0.09
    åİī
    0.09
    è´ŀ
    0.08
    å¾ĹäºĨ
    0.08
    åĽ¢éķ¿
    0.08
    reserve
    0.08
     Shel
    0.08
    éĨĩ
    0.08
    çĤ¹æ»´
    0.08
    åŃĿ
    0.08
    Activations Density 0.022%

    No Known Activations