© 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. 7400
    Prev
    Next
    INDEX
    Explanations

    salmonella

    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
    abouts
    -0.11
    ãĥĪãĥĥãĥĹ
    -0.11
    edly
    -0.11
    åķĸ
    -0.11
    rier
    -0.10
    lename
    -0.10
    /licenses
    -0.10
    èľ£
    -0.10
    管çIJĨä¸Ńå¿ĥ
    -0.09
    ams
    -0.09
    POSITIVE LOGITS
     Corps
    0.09
    /OR
    0.09
    ä»»ä½ķæŶåĢĻ
    0.08
    hv
    0.08
    ids
    0.08
    æŶèĬĤ
    0.08
    æĢĿç»´æĸ¹å¼ı
    0.08
    виÑĤ
    0.08
    Sense
    0.08
    /or
    0.08
    Activations Density 0.006%

    No Known Activations