© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52194
    Prev
    Next
    INDEX
    Explanations

    dorsal aspect, side, hood, pain

    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
    æģ¯
    -0.12
    æħµ
    -0.10
    æł¡åĽŃ
    -0.10
    çĮªèĤī
    -0.09
    éĥ½ä¸įæĺ¯
    -0.09
     smoke
    -0.08
    Smoke
    -0.08
    æ»ĭ润
    -0.08
    ä¼ijéĹ²
    -0.08
    åĽŃåĮº
    -0.08
    POSITIVE LOGITS
    èĦļ
    0.10
    è·ĸ
    0.10
    foot
    0.10
    oyer
    0.09
    èħ³
    0.09
    åĽ½éĻħå¸Ĥåľº
    0.09
    çİ¥
    0.09
    éŀĭåŃIJ
    0.09
    IFF
    0.09
    ifter
    0.09
    Activations Density 0.135%

    No Known Activations