© 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. 37735
    Prev
    Next
    INDEX
    Explanations

    must, may, should, licensed

    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
    ders
    -0.09
     adul
    -0.09
    rent
    -0.09
     Mystic
    -0.09
    庸
    -0.09
    Ĥæķ°
    -0.09
    ç´Ĭ
    -0.08
    recur
    -0.08
    å·´å·´
    -0.08
    ingleton
    -0.08
    POSITIVE LOGITS
    åı¤èĢģçļĦ
    0.10
    åģļåĪ°
    0.09
    PCM
    0.08
    èŁł
    0.08
    æ»ļçIJĥ
    0.08
    Hel
    0.08
     marathon
    0.08
    .lazy
    0.08
     tow
    0.08
    é¦Ĭ
    0.08
    Activations Density 0.017%

    No Known Activations