© 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. 54968
    Prev
    Next
    INDEX
    Explanations

    times X

    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
    å¾Īå¤ļçݩ家
    -0.11
    ÑĥÑĢ
    -0.11
    å¾Īå¤ļ人éĥ½
    -0.10
    éĵİ
    -0.10
    æŸ
    -0.10
    _ACL
    -0.10
    åŃ°
    -0.09
    å¾Īå¤ļäºĭæĥħ
    -0.09
    utsch
    -0.09
    è¢Ħ
    -0.09
    POSITIVE LOGITS
    ipe
    0.09
    æĻ®éĢļ
    0.09
    æīįåı¯ä»¥
    0.09
    -normal
    0.08
     Main
    0.08
    éĻª
    0.08
    æĻ®éĢļçļĦ
    0.08
     nearest
    0.08
    Ju
    0.08
    elight
    0.08
    Activations Density 0.062%

    No Known Activations