© 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. 21966
    Prev
    Next
    INDEX
    Explanations

    by [pronoun or proper noun]

    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
    ippers
    -0.10
    æģ¤
    -0.09
    пеÑĩаÑĤ
    -0.09
    .createClass
    -0.09
    -sheet
    -0.09
    èĦijåŃIJéĩĮ
    -0.09
    миÑĢ
    -0.08
    /cal
    -0.08
    peria
    -0.08
    org
    -0.08
    POSITIVE LOGITS
    禺
    0.10
    åĪ·æĸ°
    0.09
    å®ŀéĻħè¡ĮåĬ¨
    0.09
    å®Įç¾İ
    0.09
    ä¸ĢæĬĬ
    0.08
    è¿Ļç§įæĸ¹å¼ı
    0.08
    ä¸ĢæĬ¹
    0.08
    é«ĺéĢŁ
    0.08
    ä¸Ģè·¯
    0.08
    纳åħ¥
    0.08
    Activations Density 0.103%

    No Known Activations