© 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. 21051
    Prev
    Next
    INDEX
    Explanations

    put in

    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
    Grad
    -0.09
    èĦ¸
    -0.09
    Ñģин
    -0.09
    ingly
    -0.09
    ç´¯
    -0.09
     Grad
    -0.09
    .grad
    -0.09
    áŀĹ
    -0.08
    å¥ģ
    -0.08
    äºĭ项
    -0.08
    POSITIVE LOGITS
    ioned
    0.12
    æĻ¶ä½ĵ
    0.09
    ester
    0.08
    4
    0.08
    /respond
    0.08
    èĨĽ
    0.08
    8
    0.08
    5
    0.08
    åı£å¤´
    0.08
    errupted
    0.08
    Activations Density 0.008%

    No Known Activations