© 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. 27078
    Prev
    Next
    INDEX
    Explanations

    fiscal or financial year

    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
    ç¢Ł
    -0.09
    æľĪæľ«
    -0.09
    好å¥ĩå¿ĥ
    -0.09
    onium
    -0.09
    çīĮåŃIJ
    -0.09
     Ritch
    -0.08
     sph
    -0.08
    æŬ
    -0.08
    igy
    -0.08
    è¿·èĮ«
    -0.08
    POSITIVE LOGITS
    nox
    0.12
    RunWith
    0.10
    å¹´å¼Ģå§ĭ
    0.10
     VÄ©nh
    0.10
    rens
    0.09
    建çŃij设计
    0.09
    âĸ¸
    0.09
    建议
    0.09
    è§ĦåĪĴ设计
    0.09
    à¸ĩ
    0.08
    Activations Density 0.062%

    No Known Activations