© 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. 48919
    Prev
    Next
    INDEX
    Explanations

    visual descriptors or attributes

    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
    /left
    -0.10
    outu
    -0.09
    _outline
    -0.09
    /rest
    -0.08
    -generation
    -0.08
    oration
    -0.08
    夸
    -0.08
    ä¼ijæģ¯
    -0.08
    è£Ļ
    -0.08
    utos
    -0.08
    POSITIVE LOGITS
    éĨĴ缮
    0.12
    æłĩè¯Ń
    0.11
    æĺİç¡®æıIJåĩº
    0.10
     banner
    0.10
    åŃĹæł·
    0.10
    é²ľæĺİ
    0.10
    åı£åı·
    0.09
    banner
    0.09
    éĩijåŃĹ
    0.09
    .banner
    0.09
    Activations Density 0.136%

    No Known Activations