© 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. 34050
    Prev
    Next
    INDEX
    Explanations

    animal counts and classifications

    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
    conti
    -0.10
    _hosts
    -0.09
    OLER
    -0.09
    æħ·æħ¨
    -0.09
    éļĻ
    -0.09
    å±ħ
    -0.09
    steder
    -0.09
     bÃło
    -0.09
    ORE
    -0.09
    /packages
    -0.09
    POSITIVE LOGITS
    个ä½ĵ
    0.11
    两åıª
    0.11
    åģ¥åº·çļĦ
    0.09
    ä¸Ģåıª
    0.08
    åģ¥åº·
    0.08
    ä»Ĭå¹´
    0.08
    ç½ķè§ģ
    0.08
    壮大
    0.08
     female
    0.08
    å¾Ģå¹´
    0.08
    Activations Density 0.084%

    No Known Activations