© 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. 35657
    Prev
    Next
    INDEX
    Explanations

    presiding judge

    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
    çľ¼æ³ª
    -0.10
    ç¢Ł
    -0.10
    ish
    -0.10
    主æĦı
    -0.09
    izzo
    -0.09
    icult
    -0.08
    -news
    -0.08
    ãģªãĤĬ
    -0.08
    (ERR
    -0.08
    -than
    -0.08
    POSITIVE LOGITS
    çѵ
    0.10
    ald
    0.09
    cloth
    0.09
    hall
    0.09
    çĿĢä»ĸ
    0.09
    èijĹ
    0.08
    رة
    0.08
     над
    0.08
    ìĹ½
    0.08
    ì°©
    0.08
    Activations Density 0.009%

    No Known Activations