© 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. 18337
    Prev
    Next
    INDEX
    Explanations

    information and inquiries

    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
    _proto
    -0.08
    closure
    -0.08
    ä¸Ģçīĩ
    -0.08
    å½¼
    -0.08
    åı¤ä»£
    -0.08
    Hat
    -0.08
    mah
    -0.08
    Ø«ÙĪر
    -0.08
    eload
    -0.08
    clud
    -0.08
    POSITIVE LOGITS
    æīĵç®Ĺ
    0.12
    éĥĹ
    0.11
    è¦ģä¹Ī
    0.10
    ä¼ļ让
    0.10
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.10
     planned
    0.10
    è§ĦåĪĴ建设
    0.10
    æݪæĸ½
    0.10
    íķĺê²łëĭ¤
    0.10
    æĹ®
    0.10
    Activations Density 0.039%

    No Known Activations