© 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. 18483
    Prev
    Next
    INDEX
    Explanations

    colon, punctuation, list separator

    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
    abet
    -0.09
    IGH
    -0.09
    å§ĭ
    -0.08
    å¹³çŃī
    -0.08
    éķ¿ä¹ħ
    -0.08
     dign
    -0.08
    诸å¤ļ
    -0.08
    UNE
    -0.08
    -END
    -0.07
     tarafından
    -0.07
    POSITIVE LOGITS
    çĦ¶åIJİ
    0.13
    çĦ¶å¾Į
    0.12
    èĢĮåIJİ
    0.11
    then
    0.11
     then
    0.11
     заÑĤем
    0.10
     rá»ĵi
    0.10
    大éĺª
    0.10
    estre
    0.10
     Ø«Ùħ
    0.09
    Activations Density 0.198%

    No Known Activations