© 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. 52964
    Prev
    Next
    INDEX
    Explanations

    you are looking

    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
    æłĭ
    -0.09
    槿
    -0.09
    tos
    -0.09
    èIJĿåįľ
    -0.09
    æļĤ
    -0.09
    èģĮèĥ½éĥ¨éŨ
    -0.09
    iola
    -0.09
    è·
    -0.08
    è¥Ł
    -0.08
    å¦Ī
    -0.08
    POSITIVE LOGITS
    åŁŁåIJį
    0.09
    _PF
    0.09
    IFE
    0.08
     baÄŁlant
    0.08
    æ·±åİļçļĦ
    0.08
    conti
    0.08
    ivent
    0.08
    _TP
    0.08
    à¹Ĥà¸Ľà¸£
    0.08
    /dr
    0.08
    Activations Density 0.025%

    No Known Activations