© 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. 51280
    Prev
    Next
    INDEX
    Explanations

    demonstrate or show

    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
     Honest
    -0.09
    맹
    -0.08
    WindowSize
    -0.08
    .localized
    -0.08
    è§ģéĿ¢
    -0.08
    åĦ¿
    -0.08
    éĢ¢
    -0.08
    /linux
    -0.08
    ä¸Ĭåİ»
    -0.08
    çĦī
    -0.07
    POSITIVE LOGITS
    åIJİèĢħ
    0.11
    å¤§åĽ½
    0.10
    åīįèĢħ
    0.09
    ç´IJ
    0.09
    æ´ŀå¯Ł
    0.09
     latter
    0.09
    anal
    0.09
    ÑĩÑĮ
    0.09
    磬
    0.09
    ervo
    0.09
    Activations Density 0.073%

    No Known Activations