© 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. 6874
    Prev
    Next
    INDEX
    Explanations

    group or day labels

    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
    æĢ¥äºİ
    -0.08
    ç¢ĵ
    -0.08
    åĩŃ
    -0.08
    æ´»åĬĽ
    -0.08
     Nap
    -0.08
    iny
    -0.08
     spice
    -0.08
     tslint
    -0.08
    panse
    -0.07
    èĨĿ
    -0.07
    POSITIVE LOGITS
    odu
    0.09
    å¤ļå°ij
    0.09
    ToLocal
    0.08
    SelectionMode
    0.08
    .utcnow
    0.08
     أع
    0.08
    å°ıç±³
    0.08
    plays
    0.08
    ASC
    0.08
    第ä¸Ģ个
    0.08
    Activations Density 0.261%

    No Known Activations