© 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. 7568
    Prev
    Next
    INDEX
    Explanations

    jumper cables, Panahi, range efforts

    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
    ÙĦاÙģ
    -0.09
    ÙĪرد
    -0.09
    èij©
    -0.09
    epam
    -0.09
    çļĦç¡®
    -0.08
    Īëĭ¤
    -0.08
    çŀ§
    -0.08
     Woj
    -0.08
    à¸Ļา
    -0.08
    _OBJC
    -0.08
    POSITIVE LOGITS
    omet
    0.09
    çĻ¾å§ĵ
    0.08
    纳æĸ¯
    0.08
    æŃ£å®Ĺ
    0.08
    çĻ£
    0.08
    交éĻħ
    0.08
    å¾Ģå¤ĸ
    0.08
    ille
    0.08
    yal
    0.08
    eer
    0.08
    Activations Density 0.001%

    No Known Activations