© 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. 56626
    Prev
    Next
    INDEX
    Explanations

    restaurant names

    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
    å³ģ
    -0.09
    豪å®ħ
    -0.09
     Gala
    -0.09
    zym
    -0.08
    åı¦ä¸ĢåįĬ
    -0.08
    éĩįçĤ¹é¢ĨåŁŁ
    -0.08
     gala
    -0.08
    Edition
    -0.08
    ternal
    -0.08
    _pow
    -0.08
    POSITIVE LOGITS
    åĪĪ
    0.09
    è¿Ļ家
    0.09
    è´Ŀå°Ķ
    0.09
    åij³
    0.08
     Taste
    0.08
    ä¸į管
    0.08
    æĸ°ä¸ĸ纪
    0.08
    çĤ¹åĦ¿
    0.08
    èĩªåĬ©
    0.08
    ect
    0.08
    Activations Density 0.053%

    No Known Activations