© 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. 31692
    Prev
    Next
    INDEX
    Explanations

    cooking and timing instructions

    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
    _BU
    -0.10
    ä¸ĸçķĮ第ä¸Ģ
    -0.09
    rub
    -0.09
    顶
    -0.08
     lorem
    -0.08
    _CM
    -0.08
    alsy
    -0.08
    åĭī强
    -0.08
    伪
    -0.08
    itore
    -0.08
    POSITIVE LOGITS
    å¼Ģæ°´
    0.09
    جب
    0.09
     HuffPost
    0.08
    ãģŁãģı
    0.08
    ProcessEvent
    0.08
    缴åĪ°
    0.08
     ÑģÑĢазÑĥ
    0.08
    ÙĬÙĩ
    0.08
    è¿ĩç¨ĭå½ĵä¸Ń
    0.08
     esp
    0.08
    Activations Density 0.007%

    No Known Activations