© 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. 32959
    Prev
    Next
    INDEX
    Explanations

    -like cellular, protein, appearance, psych

    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®Įç¾İ
    -0.10
    ç¯ĩ
    -0.09
    кÑĥÑĢ
    -0.09
    ÑĥÑĩа
    -0.09
    пеÑĩ
    -0.09
    å®Įç¾İçļĦ
    -0.08
    .Escape
    -0.08
    ÅĤa
    -0.08
    ÙĥØ©
    -0.08
    çļĦç¼ĺæķħ
    -0.08
    POSITIVE LOGITS
    åIJij举
    0.10
    alam
    0.09
    åģķ
    0.08
    èµĦæºIJéħįç½®
    0.08
     CRE
    0.08
    au
    0.08
    CRE
    0.08
    isses
    0.08
    澳大
    0.08
    å¾Īæ·±
    0.08
    Activations Density 0.146%

    No Known Activations