© 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. 23339
    Prev
    Next
    INDEX
    Explanations

    computer, program, storage

    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
    ESCO
    -0.09
    çIJĨçĶ±
    -0.09
    çħ§é¡¾
    -0.08
     Dong
    -0.08
    è¥Ł
    -0.08
    补水
    -0.08
    å®Ŀå®ī
    -0.08
    éļıå¤Ħ
    -0.08
    §Ãĥ
    -0.08
    好çļĦ
    -0.08
    POSITIVE LOGITS
    计ç®Ĺæľº
    0.11
    人å±ħ
    0.10
    éħį
    0.10
    ä¸ļä½Ļ
    0.09
    ä¼łè¾ĵ
    0.09
    èĻļæĭŁ
    0.09
    è·¨è¶Ĭ
    0.09
    ä¿¡æģ¯æĬĢæľ¯
    0.09
     commission
    0.09
    ListNode
    0.09
    Activations Density 0.129%

    No Known Activations