© 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. 1907
    Prev
    Next
    INDEX
    Explanations

    new or future arrival

    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
    åĪĹ
    -0.10
    ìĭľ
    -0.09
    à¹Ħร
    -0.08
     MCS
    -0.08
    aland
    -0.08
    åĴ¬
    -0.08
    丢
    -0.08
    _PD
    -0.08
    aket
    -0.08
    anst
    -0.08
    POSITIVE LOGITS
    æĹ¶ä»£çļĦ
    0.10
    ÙĨÙĬÙĨ
    0.10
    çļĦæĹ¶ä»£
    0.10
    æĻĤ代
    0.10
    å´Ń
    0.10
    åıĮåıĮ
    0.09
    æĹ¶ä»£
    0.09
    ä¹ĭåĬ¿
    0.09
    çªĸ
    0.09
    èIJ¼
    0.09
    Activations Density 0.113%

    No Known Activations