© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19995
    Prev
    Next
    INDEX
    Explanations

    reviews

    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
    åĭ¤
    -0.10
    çĤ¯
    -0.10
    è´µ
    -0.09
    ä¸įæĪIJ
    -0.09
     заб
    -0.09
    è²´
    -0.09
    æ®ī
    -0.08
    éĿĴå¹´
    -0.08
     deb
    -0.08
     ple
    -0.08
    POSITIVE LOGITS
    unas
    0.09
     REALLY
    0.09
    ç¡®
    0.09
    unfinished
    0.08
    ÑĢÑĥÑĩ
    0.08
    åİ»æİī
    0.08
    èļ±
    0.08
    ãĤ«ãĥ«
    0.08
    upakan
    0.08
    èħ°éĥ¨
    0.08
    Activations Density 0.016%

    No Known Activations