© 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. 26687
    Prev
    Next
    INDEX
    Explanations

    protein markers and assays

    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
    ä¸Ģæ³¢
    -0.09
    身å¿ĥ
    -0.09
     mes
    -0.09
    ÑĢид
    -0.09
    uhn
    -0.08
    PHY
    -0.08
    æīĭèĩĤ
    -0.08
    æķĻ室
    -0.08
    åŀĤ缴
    -0.08
     bids
    -0.08
    POSITIVE LOGITS
    æĵİ
    0.10
    èıħ
    0.10
    æľ¬åij¨
    0.10
    /AFP
    0.09
    å´ĸ
    0.09
    æľ¬æľŁ
    0.09
    ç¢Į
    0.09
    AGES
    0.09
    èıĬ
    0.09
    rone
    0.08
    Activations Density 0.502%

    No Known Activations