© 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. 35768
    Prev
    Next
    INDEX
    Explanations

    draws, ties, trench warfare

    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
    tm
    -0.09
    ern
    -0.09
    ä¸Ĭåİ»
    -0.09
     деÑıÑĤелÑĮноÑģÑĤи
    -0.08
    TIM
    -0.08
    éĿĴ
    -0.08
     ern
    -0.08
     span
    -0.08
    éĿ©
    -0.08
    ãģ§ãģį
    -0.08
    POSITIVE LOGITS
    åĥµ
    0.11
    AGMA
    0.11
    平衡
    0.11
    åIJĦæľī
    0.11
    åħ±åIJĮåıijå±ķ
    0.10
    å¹³çŃī
    0.10
    äge
    0.10
    å¹³
    0.10
    лÑĭ
    0.10
    æĮģå¹³
    0.10
    Activations Density 0.061%

    No Known Activations