© 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. 33532
    Prev
    Next
    INDEX
    Explanations

    in before specific nouns

    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
    æ¤Ĵ
    -0.09
    å·¥ä½ľå®¤
    -0.08
     foss
    -0.08
    身边çļĦ
    -0.08
    ault
    -0.08
    _MARKER
    -0.08
     Prim
    -0.08
    âĬĸ
    -0.08
    Prim
    -0.08
    å®īåħ¨æĦŁ
    -0.07
    POSITIVE LOGITS
    .uml
    0.09
    _keeper
    0.09
    æķĽ
    0.09
    è¿Ļ项
    0.08
    æľªæĿ¥åıijå±ķ
    0.08
    å¸Ĥåľºä¸Ĭ
    0.08
    -lite
    0.08
    æľºç¥¨
    0.08
    ä¸į该
    0.08
    çĽ´è¾¾
    0.08
    Activations Density 0.090%

    No Known Activations