© 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. 33173
    Prev
    Next
    INDEX
    Explanations

    Sherlock Holmes

    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§Ľ
    -0.09
    工夫
    -0.09
    ÑĢоÑĪ
    -0.09
     Kis
    -0.09
    麽
    -0.09
    ramework
    -0.08
    ient
    -0.08
    è¿ľæ´ĭ
    -0.08
    trace
    -0.08
    è¹ĩ
    -0.08
    POSITIVE LOGITS
    sonian
    0.10
    ey
    0.10
    ëį°
    0.09
    æģ»
    0.09
    gos
    0.09
    -quarters
    0.09
    ovsky
    0.09
     اÙĦÙĨÙģس
    0.09
    ruk
    0.08
    byn
    0.08
    Activations Density 0.002%

    No Known Activations