© 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. 32752
    Prev
    Next
    INDEX
    Explanations

    or an alternative

    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
    亡
    -0.09
    å¿ł
    -0.09
    _TOUCH
    -0.09
    å´©
    -0.08
    tat
    -0.08
    ç¿Ĭ
    -0.08
    -online
    -0.08
    亲åıĭ
    -0.08
    IDI
    -0.08
    atz
    -0.08
    POSITIVE LOGITS
    aka
    0.13
     aka
    0.13
    ä¹Łå°±æĺ¯
    0.12
    æĪĸèĢħ说
    0.11
    常说
    0.11
    ä¿Ĺ称
    0.11
    åıĪ称
    0.11
    ir
    0.10
    è¿Ļ个æĹ¶ä»£
    0.09
     ‘
    0.09
    Activations Density 0.132%

    No Known Activations