© 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. 26864
    Prev
    Next
    INDEX
    Explanations

    pull off or push through

    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
    å®ŀæĸ½ç»ĨåĪĻ
    -0.09
    çļĦ缮åħī
    -0.09
     Griff
    -0.08
    igs
    -0.08
    é«ĺæłĩåĩĨ
    -0.08
    å®Ŀè´µ
    -0.08
    é»Ħéĩij
    -0.08
     Renew
    -0.08
    æ¶Į
    -0.08
    ijľ
    -0.08
    POSITIVE LOGITS
    amel
    0.09
    Merit
    0.09
    è¿Ļåľº
    0.09
    æĭīåĬ¨
    0.09
    è¿Ļä¸ī个
    0.09
    æĦıæĥ³ä¸įåĪ°
    0.09
    å¥ĩ迹
    0.08
    èĨ»
    0.08
    æ°´åŁŁ
    0.08
    RuntimeObject
    0.08
    Activations Density 0.003%

    No Known Activations