© 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. 17194
    Prev
    Next
    INDEX
    Explanations

    self-aligned, self-ad, self-boot, self-built

    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
    vik
    -0.09
    å®ŀå®ŀåľ¨åľ¨
    -0.09
    enda
    -0.08
     Bieber
    -0.08
    MEA
    -0.08
    饼
    -0.08
    让å®ĥ
    -0.08
    uo
    -0.08
    é©°
    -0.08
     tÃŃ
    -0.08
    POSITIVE LOGITS
    verständlich
    0.10
    为主
    0.09
    enu
    0.08
    ç¾
    0.08
    æİĴ污
    0.08
    éĤĪ
    0.08
    uctions
    0.08
    ей
    0.08
    å§ĵ
    0.08
    resume
    0.08
    Activations Density 0.078%

    No Known Activations