© 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. 51298
    Prev
    Next
    INDEX
    Explanations

    under law or to the extent possible

    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
    azz
    -0.09
    èĢĥå¯Ł
    -0.08
    ä»»
    -0.08
    essay
    -0.08
    è¿Ī
    -0.08
    å¢ŀéĩı
    -0.07
    ç¿Ķ
    -0.07
     Bat
    -0.07
    .android
    -0.07
    éĴĪ对æĢ§
    -0.07
    POSITIVE LOGITS
    ogl
    0.10
    NOP
    0.10
    èĩªæ²»åĮº
    0.09
    éĻĮçĶŁäºº
    0.09
    æĿĮ
    0.09
    wit
    0.09
    루
    0.09
     cá»ķ
    0.09
    à¸Ńม
    0.09
    olver
    0.09
    Activations Density 0.020%

    No Known Activations