© 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. 30333
    Prev
    Next
    INDEX
    Explanations

    the selection

    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
    dì
    -0.09
    è¹Ħ
    -0.09
    ä¸Ģå¿ĥ
    -0.08
    éĹ´
    -0.08
     Ott
    -0.08
     unf
    -0.08
    Intern
    -0.08
    å¾Īå¤ļæŶåĢĻ
    -0.08
    inet
    -0.08
    寰
    -0.08
    POSITIVE LOGITS
    íĥĪ
    0.11
    çijĹ
    0.10
    iban
    0.10
    深交
    0.10
    箩
    0.10
    éĿ¢å°į
    0.10
    .shtml
    0.09
    椰
    0.09
    æĸ§
    0.09
    èĪ£
    0.09
    Activations Density 0.091%

    No Known Activations