© 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. 36565
    Prev
    Next
    INDEX
    Explanations

    creative Commons, Suite, hands, writing, Solutions

    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
    ç¡®åĪĩ
    -0.09
    ioned
    -0.09
    èĤ¯
    -0.09
    忾
    -0.08
    KA
    -0.08
    æĴ¼
    -0.08
    åѤ
    -0.08
    EntityType
    -0.08
    çª
    -0.08
    åħ±äº«åįķ车
    -0.08
    POSITIVE LOGITS
    uze
    0.11
    äºĽ
    0.10
    PECT
    0.09
    ulously
    0.09
    hare
    0.09
    yles
    0.09
    aily
    0.08
    èĻº
    0.08
    viously
    0.08
    istar
    0.08
    Activations Density 0.012%

    No Known Activations