© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40158
    Prev
    Next
    INDEX
    Explanations

    names or phrases following prepositions

    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
    Negative Logits
    æĺ¯å¤ļä¹Ī
    -0.10
    éŃij
    -0.09
    è¿Ļæĺ¯ä¸Ģç§į
    -0.08
    ÑĩаÑģÑĤ
    -0.08
    éĿ¢è²Į
    -0.08
    æĪij没æľī
    -0.08
    URITY
    -0.08
    ising
    -0.08
    Configs
    -0.08
    å¾µ
    -0.08
    POSITIVE LOGITS
    éħįåIJĪ
    0.09
    /of
    0.09
    arbeit
    0.08
    atsapp
    0.08
    esser
    0.08
    éĢ¡
    0.08
    å²ĺ
    0.08
    æĿijéĩĮ
    0.08
    éĢīå®ļ
    0.08
    .gs
    0.08
    Activations Density 0.327%

    No Known Activations