© 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. 57335
    Prev
    Next
    INDEX
    Explanations

    surnames starting with i

    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
    abilities
    -0.09
     ÐŃÑĤ
    -0.09
    ayo
    -0.09
    æ»´
    -0.09
     nails
    -0.08
    éĴī
    -0.08
     nailed
    -0.08
    CLAIM
    -0.08
    _ASSUME
    -0.08
    åĵģ
    -0.08
    POSITIVE LOGITS
    为æĬĵ
    0.09
    æ´ĹèĦ¸
    0.09
    åĽłä¸ºä½ł
    0.09
    ç¼Ļ
    0.08
    ç¼Ķ
    0.08
    éģĹçķĻ
    0.08
    ä»ĸçŁ¥éģĵ
    0.08
    UPER
    0.08
    å¼Ń
    0.08
    çģ«çĥ§
    0.08
    Activations Density 0.152%

    No Known Activations