© 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. 21827
    Prev
    Next
    INDEX
    Explanations

    court order

    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
    夫
    -0.10
    è¿ĩå¾Ĺ
    -0.10
    .RunWith
    -0.09
    çĶ³æĬ¥
    -0.09
    overe
    -0.09
    åħ¨èĩªåĬ¨
    -0.09
    lage
    -0.09
    廨
    -0.09
    enos
    -0.09
    èĭ¡
    -0.09
    POSITIVE LOGITS
    abor
    0.09
    lass
    0.08
    çĩĥçħ¤
    0.08
    åģļ人
    0.08
    çĽ¸ä¿¡å¤§å®¶
    0.08
    ATS
    0.08
    elper
    0.08
    å¿ħä¸įåı¯
    0.07
    anky
    0.07
    å¾Ĭ
    0.07
    Activations Density 0.127%

    No Known Activations