© 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. 37947
    Prev
    Next
    INDEX
    Explanations

    availability of resources

    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
    帮åĬ©ä¼ģä¸ļ
    -0.09
    ä¸İä¼Ĺ
    -0.09
    éĿ¢å®¹
    -0.09
    æĦĢ
    -0.09
    è§ĦåĪĴ设计
    -0.09
    æĹĹèĪ°
    -0.08
    åĸĿèĮ¶
    -0.08
    åĤĪ
    -0.08
    æľīæĦıä¹ī
    -0.08
    ạn
    -0.08
    POSITIVE LOGITS
     availability
    0.17
    availability
    0.15
     available
    0.15
    .available
    0.15
     Availability
    0.14
     disponibles
    0.14
    available
    0.14
    _available
    0.13
     Available
    0.13
    Availability
    0.13
    Activations Density 0.088%

    No Known Activations