© 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. 61672
    Prev
    Next
    INDEX
    Explanations

    sports and cellular biology 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
    åħ¨èº«
    -0.10
    piel
    -0.10
    anism
    -0.09
    æĪĸå¤ļ
    -0.09
    åĿŁ
    -0.09
    TRL
    -0.09
    /operators
    -0.09
    OfWork
    -0.09
    æī¯
    -0.09
    emble
    -0.09
    POSITIVE LOGITS
    åĪ°ä½į
    0.10
    èĶ
    0.09
    ç»ij
    0.08
    oad
    0.08
    次æķ°
    0.08
    éĥ¨åī¯
    0.08
    迪æĭľ
    0.08
    rint
    0.07
    ä½ıäºĨ
    0.07
    æľ¬åij¨
    0.07
    Activations Density 0.001%

    No Known Activations