© 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. 58990
    Prev
    Next
    INDEX
    Explanations

    mailing address

    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
    ourt
    -0.09
    uations
    -0.09
    ein
    -0.09
    æī®æ¼Ķ
    -0.09
    AREN
    -0.09
    æĴĩ
    -0.08
    arine
    -0.08
    é»Ħæĺı
    -0.08
    éĢĤ
    -0.08
    æ½ľ
    -0.08
    POSITIVE LOGITS
    éĤ®å¯Ħ
    0.13
    ãĢĴ
    0.11
    å¿«éĢĴ
    0.10
    çĻĸ
    0.09
     address
    0.09
     rap
    0.09
    éĢģè¾¾
    0.09
    åľ°åĿĢ
    0.09
     visceral
    0.09
    atically
    0.09
    Activations Density 0.033%

    No Known Activations