© 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. 48098
    Prev
    Next
    INDEX
    Explanations

    large quantities

    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¸īæĿ¡
    -0.10
    _aspect
    -0.09
    _apps
    -0.09
    AspectRatio
    -0.09
    sense
    -0.09
    讪
    -0.08
     Elastic
    -0.08
    ç¥ĸ
    -0.08
    绿èī²éĢļéģĵ
    -0.08
    éĵį
    -0.08
    POSITIVE LOGITS
    éĿŀ常å¤ļ
    0.14
     thousands
    0.14
     hundreds
    0.13
    Hundreds
    0.13
     billions
    0.13
     dozens
    0.13
    æĹłæķ°
    0.13
    ãģŁãģıãģķãĤĵ
    0.13
     millions
    0.12
    大éĩıçļĦ
    0.12
    Activations Density 0.123%

    No Known Activations