© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17060
    Prev
    Next
    INDEX
    Explanations

    initially

    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
    ä¼ĹæīĢ
    -0.10
    ä¸ĩéĩĮ
    -0.10
    åı¯æĢľ
    -0.10
    æ´½
    -0.09
    缺åı£
    -0.09
    pcodes
    -0.08
    atos
    -0.08
    æį®æĤī
    -0.08
    orra
    -0.08
    ä¸įåĨį
    -0.08
    POSITIVE LOGITS
     initially
    0.32
    èµ·åĪĿ
    0.28
    æľĢåĪĿ
    0.26
    æľĢåĪĿçļĦ
    0.26
    åĪĿæľŁ
    0.25
    ä¸Ģå¼Ģå§ĭ
    0.24
     Initially
    0.21
    Initially
    0.21
    ä¹ĭåĪĿ
    0.21
    缴åĪ°
    0.21
    Activations Density 0.181%

    No Known Activations