© 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. 48437
    Prev
    Next
    INDEX
    Explanations

    enthusiast or fan

    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
    æķĻè®Ń
    -0.10
    åŁİ乡
    -0.09
     Hubb
    -0.09
    ä½ľçī©
    -0.09
    åİĤåķĨ
    -0.09
    หมà¸Ķ
    -0.09
    emie
    -0.09
    _vendor
    -0.09
    .safe
    -0.08
    åĴ¨è¯¢æľįåĬ¡
    -0.08
    POSITIVE LOGITS
    çĪ±å¥½èĢħ
    0.14
    è¿·
    0.14
    çĥŃçĪ±
    0.13
    fans
    0.13
    åıijçĥ§
    0.12
    主ä¹īèĢħ
    0.11
    åĸľæ¬¢
    0.11
     лÑİб
    0.10
    çĪ±ç¾İ
    0.10
    好ãģį
    0.10
    Activations Density 0.137%

    No Known Activations