© 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. 39969
    Prev
    Next
    INDEX
    Explanations

    hopes and desires

    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
    umen
    -0.09
    ÑĢÑĭв
    -0.08
    éĿŀ常çļĦ
    -0.08
    åIJĵå¾Ĺ
    -0.08
    å¾Īæľī
    -0.08
     tÃŃch
    -0.08
    æ°´æ³µ
    -0.08
    enes
    -0.07
    èĴ²
    -0.07
    is
    -0.07
    POSITIVE LOGITS
    å¸ĮæľĽ
    0.14
     hopes
    0.14
    lessly
    0.13
    渺
    0.12
     hoped
    0.12
     hope
    0.12
    çĽ¼
    0.11
    è§İ
    0.11
    ä¸ĭ次
    0.11
    ä¸ĩä¸Ģ
    0.11
    Activations Density 0.059%

    No Known Activations