© 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. 61980
    Prev
    Next
    INDEX
    Explanations

    baseball teams and seasons

    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
    è¶Ĭéĩİ
    -0.10
    é¢Ħè§ģ
    -0.09
    çĻ»å±±
    -0.09
    éĩľ
    -0.09
    oble
    -0.09
    aley
    -0.09
    ÑĩаÑģÑĤ
    -0.09
    ä¸įçķĻ
    -0.09
     Haley
    -0.09
    igham
    -0.09
    POSITIVE LOGITS
     baseball
    0.11
     Baseball
    0.10
    æĬķ
    0.10
    uras
    0.10
     SSH
    0.09
    çĶŁäº§ç»ıèIJ¥
    0.09
     ssh
    0.08
    implicitly
    0.08
    OPS
    0.08
     strikeouts
    0.08
    Activations Density 0.329%

    No Known Activations