© 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. 62088
    Prev
    Next
    INDEX
    Explanations

    karma yoga

    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
    èĩĬ
    -0.10
    -General
    -0.09
    acid
    -0.09
    owie
    -0.09
    æ³Ĭ
    -0.08
    евиÑĩ
    -0.08
    殿ä¸ĭ
    -0.08
    _GENERAL
    -0.08
    æĩĤäºĭ
    -0.08
     Eph
    -0.08
    POSITIVE LOGITS
    èĥ½éĩı
    0.12
    çļĦèĥ½éĩı
    0.11
    祷
    0.11
    ç¥Ī祷
    0.11
    æĦŁæĥħ
    0.10
    æĢ¨
    0.10
    ç¥Ī
    0.10
    çľĭçĶµè§Ĩ
    0.10
     prayers
    0.10
    缮æłĩ
    0.10
    Activations Density 0.036%

    No Known Activations