© 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. 20126
    Prev
    Next
    INDEX
    Explanations

    cell cycle stages

    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
    廪
    -0.10
     кÑĢай
    -0.09
    INGER
    -0.09
    à¸Ĺะ
    -0.08
    人éĹ´
    -0.08
    æĹº
    -0.08
    èĤ©è´Ł
    -0.08
    izzo
    -0.08
    alth
    -0.08
    ç¥ŀ
    -0.08
    POSITIVE LOGITS
    èĢ½
    0.09
    迸
    0.08
    è±³
    0.08
    çݯç»ķ
    0.08
    å¤ĩæĪĺ
    0.08
    èĦĨå¼±
    0.08
    çݯ
    0.08
     timestep
    0.08
    æĹłå£°
    0.08
     Broadcast
    0.07
    Activations Density 0.217%

    No Known Activations