© 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. 3010
    Prev
    Next
    INDEX
    Explanations

    postseason and sports 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
    Ợ
    -0.10
    æĪĸå¤ļ
    -0.09
     olan
    -0.09
    esthes
    -0.09
    emic
    -0.09
    venir
    -0.08
    æĻ®åıĬ
    -0.08
     electrom
    -0.08
    ther
    -0.08
     дов
    -0.08
    POSITIVE LOGITS
    æĿ¥ä¸´
    0.09
    stalk
    0.09
    tern
    0.09
    çıŃ
    0.08
    æĵį
    0.08
    idge
    0.08
    IFF
    0.08
    çĶ¨å·¥
    0.08
    achs
    0.08
    ouch
    0.08
    Activations Density 0.003%

    No Known Activations