© 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. 57190
    Prev
    Next
    INDEX
    Explanations

    & abbreviations

    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»ıéªĮåĴĮ
    -0.10
    omorphic
    -0.09
    ÑģÑĮ
    -0.09
    æĻ°
    -0.09
    ãģªãģľ
    -0.09
    ifications
    -0.09
    lets
    -0.09
    åıijå±ķåīįæĻ¯
    -0.08
    ules
    -0.08
    åĩłçĤ¹
    -0.08
    POSITIVE LOGITS
    amp
    0.17
    /OR
    0.13
    /or
    0.11
    emsp
    0.10
    ners
    0.10
    nbsp
    0.10
    大家åĪĨ享
    0.10
    Ñģкоп
    0.09
    ning
    0.09
    Ñģком
    0.09
    Activations Density 0.027%

    No Known Activations