© 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. 36213
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating status or origin

    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
    æĪIJ为ä¸Ģ个
    -0.10
    ä¸Ģç¬Ķ
    -0.10
    /OR
    -0.09
    ument
    -0.09
    è´§æºIJ
    -0.09
    ä¸ĢèĦļ
    -0.09
    éļıæŶéļı
    -0.09
     POLIT
    -0.09
    çļĦåĪ°æĿ¥
    -0.09
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.09
    POSITIVE LOGITS
    vier
    0.09
    Outside
    0.08
     elsewhere
    0.08
    ä¸įä¹ħ
    0.08
    _CANCEL
    0.08
    çªĴæģ¯
    0.08
    ç²ľ
    0.08
    èķĻ
    0.08
    éĩĮéĿ¢æľī
    0.08
    缮çĿ¹
    0.08
    Activations Density 0.244%

    No Known Activations