© 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. 21951
    Prev
    Next
    INDEX
    Explanations

    parts or properties

    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
    渲
    -0.12
    没éĶĻ
    -0.10
    ä¸įçĶĺ
    -0.10
    顽强
    -0.10
    éĿ¡
    -0.10
    è¿Ļæł·ä¸Ģ
    -0.09
    æIJŀ好
    -0.09
    ihad
    -0.09
    etype
    -0.09
    æ¡Ģ
    -0.09
    POSITIVE LOGITS
    onium
    0.08
    éŀĺ
    0.08
    éĽı
    0.08
    Enumerable
    0.07
     Nä
    0.07
    _nn
    0.07
    "]."
    0.07
    .EXTRA
    0.07
    æ³¾
    0.07
    NAL
    0.07
    Activations Density 1.575%

    No Known Activations