© 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. 19626
    Prev
    Next
    INDEX
    Explanations

    periods of time

    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
    éĤ£è¾¹
    -0.10
    AREA
    -0.09
    æİĸ
    -0.09
    å¸
    -0.09
    _NEED
    -0.09
    ðŁİ²
    -0.09
    åºľ
    -0.09
    æµ·æĬ¥
    -0.08
    çļĦæĥħæĦŁ
    -0.08
     GIF
    -0.08
    POSITIVE LOGITS
    ä¸Ģ段
    0.14
    ä¸Ģ段æŶéĹ´
    0.13
     stint
    0.12
     periods
    0.12
    ä¼ijæģ¯
    0.11
    段æŶéĹ´
    0.11
    è¿Ļ段
    0.10
    çŁŃæļĤ
    0.10
     Weeks
    0.10
     spells
    0.10
    Activations Density 0.123%

    No Known Activations