© 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. 30521
    Prev
    Next
    INDEX
    Explanations

    abstract or scientific terms

    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
    足
    -0.09
    åł¡åŀĴ
    -0.09
     Loves
    -0.09
    åĪ¸
    -0.09
    æĻ¨
    -0.09
    ocate
    -0.08
    éľŃ
    -0.08
    æłī
    -0.08
    æ¸ħæĸ°
    -0.08
    OLA
    -0.08
    POSITIVE LOGITS
    åħ±æĮ¯
    0.10
    è½®åĽŀ
    0.09
    æĴŀ
    0.09
    ä¸į稳å®ļ
    0.09
    æĥij
    0.09
    è¿ijè·Ŀ离
    0.08
    éĴµ
    0.08
    èĽĩ
    0.08
    éĩįåŀĭ
    0.08
    ÑĢаж
    0.08
    Activations Density 0.215%

    No Known Activations