© 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. 17791
    Prev
    Next
    INDEX
    Explanations

    end or ending a situation

    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
    venir
    -0.11
    æ¯ĵ
    -0.10
    åĤį
    -0.10
    èµ·æĿ¥äºĨ
    -0.09
    atura
    -0.09
    é½IJåħ¨
    -0.09
    ãģ©ãģĵãĤį
    -0.09
    egin
    -0.09
    akedown
    -0.09
    æŀķ头
    -0.09
    POSITIVE LOGITS
    urance
    0.10
    åIJĪä½ľåħ³ç³»
    0.09
    è¶Ł
    0.08
    ä¸įäºĨ
    0.08
    urable
    0.08
    å¾ģç¨ĭ
    0.08
    æĿŁç¼ļ
    0.08
    inous
    0.08
    acho
    0.08
    åѤåįķ
    0.08
    Activations Density 0.028%

    No Known Activations