© 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. 6765
    Prev
    Next
    INDEX
    Explanations

    Lexology, Wet Planet, HeraldNet, Levy, Dick's

    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
    åįİ为
    -0.08
    åĨį说
    -0.08
    å½ĵåľ°æĶ¿åºľ
    -0.07
     deb
    -0.07
    -uppercase
    -0.07
    ending
    -0.07
     efficiencies
    -0.07
    ocos
    -0.07
     amps
    -0.07
    该éĻ¢
    -0.07
    POSITIVE LOGITS
    è¿Ļè¾¹
    0.14
    涯
    0.10
    verse
    0.10
    Operand
    0.09
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    رج
    0.09
    Brit
    0.09
    è¿Ļçīĩ
    0.09
    éĻªä½ł
    0.09
     оÑĢганизм
    0.09
    Activations Density 0.385%

    No Known Activations