© 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. 18816
    Prev
    Next
    INDEX
    Explanations

    Quentin Tarantino

    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
     вÑĢемен
    -0.09
    ä¸Ģå¹ħ
    -0.09
    ings
    -0.09
     trÃŃ
    -0.09
    thew
    -0.08
     inception
    -0.08
    NESS
    -0.08
    8
    -0.08
    åĨ·æ°´
    -0.08
    å¼ĭ
    -0.08
    POSITIVE LOGITS
    arily
    0.11
    åĽŀäºĭ
    0.10
    å¨ĥ
    0.10
    nier
    0.09
    ÑĪка
    0.09
    ernet
    0.09
    airy
    0.09
    绣çŃ¹æİ¨è¿Ľ
    0.09
     nostr
    0.08
    åݦ
    0.08
    Activations Density 0.007%

    No Known Activations