© 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. 50796
    Prev
    Next
    INDEX
    Explanations

    runway open

    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
    ç½Ł
    -0.08
     HT
    -0.08
    æĤĴ
    -0.08
     Minds
    -0.08
    äºĨä¸Ģç³»åĪĹ
    -0.08
    åĪ·
    -0.07
    第äºĮæī¹
    -0.07
    顺
    -0.07
    æĿ¥åİĨ
    -0.07
     Insider
    -0.07
    POSITIVE LOGITS
    åĸ»
    0.15
    ä¸Ģæł·çļĦ
    0.13
    æ¯Ķåĸ»
    0.13
    åijĽ
    0.10
     metaphor
    0.10
    sam
    0.10
    ä¸Ģæł·
    0.09
    人çĶŁçļĦ
    0.09
    -Am
    0.09
    éĤ£ä¸ªäºº
    0.09
    Activations Density 0.112%

    No Known Activations