© 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. 39563
    Prev
    Next
    INDEX
    Explanations

    any, other, some, every

    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
    avi
    -0.08
    举
    -0.08
    imat
    -0.08
    isan
    -0.08
    飨
    -0.08
    1
    -0.07
    åIJĬ
    -0.07
    9
    -0.07
    7
    -0.07
    8
    -0.07
    POSITIVE LOGITS
    çªģå¦Ĥåħ¶
    0.11
    éĵ³
    0.10
    ç²
    0.10
    ç«¥
    0.10
    åĽłä¸ºåľ¨
    0.09
    ourd
    0.09
    å·§åħĭåĬĽ
    0.09
    olley
    0.09
    èĬľ
    0.09
    éĤ£ä¸ĢåĪ»
    0.09
    Activations Density 0.103%

    No Known Activations