© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    asking for clues

    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
    عÙħ
    -0.09
    utes
    -0.09
    éĵµ
    -0.08
     ÑĩаÑģÑĤÑĮ
    -0.08
    icable
    -0.08
    åĽłä¸ºä»ĸ
    -0.08
    гÑĥ
    -0.08
     ìĿ´ë£¨
    -0.08
    losure
    -0.08
    ozilla
    -0.08
    POSITIVE LOGITS
    lessly
    0.14
    线索
    0.11
    ä¸įæ¸ħ
    0.10
    heads
    0.10
    fulness
    0.09
    è°ľ
    0.09
    вали
    0.08
    tte
    0.08
    lessness
    0.08
    æİĩ
    0.08
    Activations Density 0.008%

    No Known Activations