© 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. 26502
    Prev
    Next
    INDEX
    Explanations

    sharing and spreading content

    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
    ä¸įè§ģ
    -0.10
    okus
    -0.09
    Fine
    -0.09
    zik
    -0.09
    窨
    -0.09
    èħ»
    -0.09
    大å®Ĺ
    -0.08
    èµĭ
    -0.08
    æīĵå¾Ĺ
    -0.08
    arness
    -0.08
    POSITIVE LOGITS
    ä¼łæĴŃ
    0.20
    æī©æķ£
    0.14
    转åıij
    0.14
     ÑĢаÑģпÑĢоÑģÑĤÑĢан
    0.13
    spread
    0.13
    ç»ĻåĪ«äºº
    0.13
     spread
    0.12
     spreads
    0.12
    Spread
    0.12
     ÑĢаÑģпÑĢоÑģÑĤ
    0.12
    Activations Density 0.090%

    No Known Activations