© 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. 20314
    Prev
    Next
    INDEX
    Explanations

    engine and combustion

    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
    客æµģ
    -0.11
    çĸıéĢļ
    -0.11
    管çIJĨæĿ¡ä¾ĭ
    -0.10
    榨
    -0.09
    è¡Į人
    -0.09
    æŀ¢
    -0.09
    æī©å¤§
    -0.09
    ä½ľåĿĬ
    -0.09
    çħİ
    -0.09
    笺
    -0.09
    POSITIVE LOGITS
     rv
    0.09
    RV
    0.09
    legate
    0.09
    à¹Ħ
    0.08
    éĴ±è´¢
    0.08
    rv
    0.08
    (rv
    0.08
    à¸ĩ
    0.08
     ngu
    0.08
    çİĭåħĪçĶŁ
    0.08
    Activations Density 0.117%

    No Known Activations