© 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. 62521
    Prev
    Next
    INDEX
    Explanations

    protest/matter/wallace/street

    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
    åĮĢ
    -0.10
    вал
    -0.09
    æĴ©
    -0.09
    éal
    -0.09
    Senate
    -0.09
    .getInfo
    -0.08
    è¿Ń
    -0.08
    好çľĭçļĦ
    -0.08
    ÑĢаб
    -0.08
    åķ¬
    -0.08
    POSITIVE LOGITS
    è¶Ĭå¤ļ
    0.09
    .um
    0.08
    éķ¿æĺ¥
    0.08
    umbo
    0.08
    /cop
    0.08
    çľ¼éĩĮ
    0.08
    æľŁéĸĵ
    0.08
    æĹ¥å¤ľ
    0.08
    aux
    0.08
    uddy
    0.08
    Activations Density 0.004%

    No Known Activations