© 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. 33855
    Prev
    Next
    INDEX
    Explanations

    date, first, won, finally

    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
    odem
    -0.10
    积
    -0.10
    åĨł
    -0.09
    ohn
    -0.09
    说åĩºæĿ¥
    -0.09
    apor
    -0.09
    plain
    -0.09
    pla
    -0.09
    à¹Ģà¸ľà¸¢à¹ģà¸ŀร
    -0.08
    楼ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    éķ¿éĢĶ
    0.09
    èĩ§
    0.09
    éī´åĪ«
    0.09
    计åĪĴçĶŁèĤ²
    0.09
    è¡Įéķ¿
    0.09
    平衡
    0.08
    ä¸Ģæ³¢
    0.08
     NYT
    0.08
    绵
    0.08
    åĶĨ
    0.08
    Activations Density 0.011%

    No Known Activations