© 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. 53492
    Prev
    Next
    INDEX
    Explanations

    specific nouns and organizations

    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
    å¥ij
    -0.11
     Madden
    -0.10
    çķħ
    -0.10
    åIJ¬çĿĢ
    -0.09
    åĢ¼å®Ī
    -0.09
    idget
    -0.08
    oley
    -0.08
     админиÑģÑĤÑĢа
    -0.08
    çıį
    -0.08
    ystore
    -0.08
    POSITIVE LOGITS
    éĶ»
    0.11
    æİĪä¿¡
    0.10
    æĿŃ
    0.09
    .period
    0.09
    æĵħèĩª
    0.09
    enha
    0.08
    ç¿©
    0.08
    èĺħ
    0.08
    åľ°ä¸Ń
    0.08
    ä¸į足
    0.08
    Activations Density 0.091%

    No Known Activations