© 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. 31218
    Prev
    Next
    INDEX
    Explanations

    describing qualities or states

    np_acts-logits-general · gemini-2.5-flash-lite

    words that signal strong subjective emphasis or novelty (emotive/adjective or adverbial hype like "new", "magically", "never-before-seen", or other high-intensity descriptors).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    apas
    -0.09
    æ»´
    -0.09
     amen
    -0.08
    ساÙĨ
    -0.08
    åŃ£
    -0.08
    UGE
    -0.08
    æīįæĺ¯
    -0.08
    æīĢ以æĪij
    -0.08
    eming
    -0.08
    åĺ²ç¬ij
    -0.07
    POSITIVE LOGITS
    ä¸įç»ı
    0.09
    å·§åIJĪ
    0.09
    loon
    0.09
    ÑģÑĤвие
    0.09
    sic
    0.09
    æĥ³æī¾
    0.09
    ToDevice
    0.08
    æľ¬è½®
    0.08
    ç¼¢
    0.08
    )|(
    0.08
    Activations Density 1.363%

    No Known Activations