© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53378
    Prev
    Next
    INDEX
    Explanations

    anticipation

    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
    itionally
    -0.09
    yster
    -0.09
    rock
    -0.09
    æĺ¥é£İ
    -0.08
    ãģı
    -0.08
    iders
    -0.08
    åĪĨãģij
    -0.08
    ellers
    -0.08
    æŃ£åľ¨è¿Ľè¡Į
    -0.08
    udd
    -0.08
    POSITIVE LOGITS
    éĻIJãĤĬ
    0.11
    ä¸ĩåĪĨ
    0.11
    å·²ä¹ħçļĦ
    0.11
    ç¾İæĻ¯
    0.09
    ç½ijåıĭ们
    0.09
    ably
    0.09
    ÑĤе
    0.09
    å·²ä¹ħ
    0.09
     noqa
    0.09
     Downs
    0.09
    Activations Density 0.013%

    No Known Activations