© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20090
    Prev
    Next
    INDEX
    Explanations

    look like adjective

    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
    laps
    -0.10
    imon
    -0.09
    ogue
    -0.09
    èĪĴ
    -0.09
    æģ©
    -0.08
    çĸı
    -0.08
    .LayoutStyle
    -0.08
    essa
    -0.08
    forg
    -0.08
     pound
    -0.08
    POSITIVE LOGITS
    磾
    0.10
    åĥı个
    0.10
    å¼ij
    0.10
    常æĢģåĮĸ
    0.09
    åıł
    0.09
    娲
    0.09
    å°½éĩı
    0.09
    è²Ķ
    0.09
    æĺ¾å¾Ĺ
    0.09
    èݲ
    0.09
    Activations Density 0.038%

    No Known Activations