© 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. 30953
    Prev
    Next
    INDEX
    Explanations

    release / releases

    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
    æ§Ł
    -0.10
    ignon
    -0.10
    æİ°
    -0.09
    ç«łç¨ĭ
    -0.09
    è¢į
    -0.09
    ç½Ĥ
    -0.09
    åĪĩåī²
    -0.09
     PIT
    -0.09
    ä¸į失
    -0.09
    locator
    -0.09
    POSITIVE LOGITS
    .Release
    0.11
     release
    0.11
     releases
    0.10
    æľīéĴ±
    0.10
    -release
    0.10
    release
    0.10
     RELEASE
    0.09
    /release
    0.09
    RELEASE
    0.09
    .release
    0.09
    Activations Density 0.026%

    No Known Activations