© 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. 33080
    Prev
    Next
    INDEX
    Explanations

    draw curved things

    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
    .getRight
    -0.10
    SpaceItem
    -0.09
     Wide
    -0.09
    ä¸įåIJĮäºİ
    -0.09
    åIJįçīĮ
    -0.09
     Äijầy
    -0.09
    Wide
    -0.08
    atat
    -0.08
    ButtonTitles
    -0.08
    çķ
    -0.08
    POSITIVE LOGITS
    æīĭæ³ķ
    0.10
     applied
    0.10
    .Apply
    0.08
    æķĪæŀľ
    0.08
     sculpt
    0.08
    篷
    0.08
    éĢıè§Ĩ
    0.08
    çļ´
    0.08
     apply
    0.08
    èĶ¬
    0.07
    Activations Density 0.241%

    No Known Activations