© 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. 1583
    Prev
    Next
    INDEX
    Explanations

    additional information

    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
    èĥĮ
    -0.10
    éī´
    -0.09
    æ½Ń
    -0.08
    失æݧ
    -0.08
    unan
    -0.08
     theor
    -0.08
    íĥĪ
    -0.08
    une
    -0.08
     ngá»Ļ
    -0.08
    çIJ¦
    -0.07
    POSITIVE LOGITS
    çļĦç¼ĺæķħ
    0.10
    è¦ģçŁ¥éģĵ
    0.10
    çŁ¥éģĵèĩªå·±
    0.10
    oze
    0.09
    olics
    0.09
    ä¸Ģ件äºĭæĥħ
    0.09
    ä¸Ģåij³
    0.09
    讲究
    0.09
    .fm
    0.08
     наÑĢÑĥÑĪен
    0.08
    Activations Density 0.010%

    No Known Activations