© 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. 61617
    Prev
    Next
    INDEX
    Explanations

    `` $$ math or code block delimiters

    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
    ÑģÑĮ
    -0.08
    æ²ĵ
    -0.08
    ork
    -0.07
    çĬ¶åĨµ
    -0.07
    è¯Ł
    -0.07
    ä¸įç»ı
    -0.07
    ãģ¾ãģĹãģ¦
    -0.07
    даÑİÑĤ
    -0.07
     rightful
    -0.07
    åľ°è¯´
    -0.07
    POSITIVE LOGITS
    burgh
    0.10
    ANGO
    0.10
    moid
    0.09
    以ä¸Ĭ
    0.09
    uke
    0.09
    馥
    0.09
    ibrator
    0.09
    ograd
    0.09
    _ATTRIBUTE
    0.09
    è¿Ļä¸ĢåĪ»
    0.08
    Activations Density 0.269%

    No Known Activations