© 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. 48014
    Prev
    Next
    INDEX
    Explanations

    shows volume or price

    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
    Violation
    -0.11
    çĵ¶
    -0.10
    è·Ŀ
    -0.09
    ëĦ·
    -0.09
    èĥŃ
    -0.09
    è³´
    -0.09
    æĢ§è´¨
    -0.09
    ì»
    -0.09
    .Components
    -0.08
    ãĤŃãĥ¥
    -0.08
    POSITIVE LOGITS
    è®°è½½
    0.12
    åĩºæĿ¥çļĦ
    0.10
    èµĦæĸĻæĺ¾ç¤º
    0.09
    åıįæĺł
    0.09
    æµģæ°´
    0.09
    人çĶŁ
    0.08
    æ°´æµģ
    0.08
    hung
    0.08
     sug
    0.08
    ä»ĭ
    0.08
    Activations Density 0.070%

    No Known Activations