© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36486
    Prev
    Next
    INDEX
    Explanations

    home + noun

    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
    æĿ¥è®¿
    -0.09
    aph
    -0.09
    å¤ļåIJĥ
    -0.08
    egov
    -0.08
    æ²³æµģåŁŁ
    -0.08
    课æĸĩ
    -0.08
    dbuf
    -0.08
    èį¯å¸Ī
    -0.08
    abox
    -0.08
    GestureRecognizer
    -0.08
    POSITIVE LOGITS
    åħĥ
    0.10
    ista
    0.09
    修饰
    0.09
    é¹ij
    0.08
    æѦè£ħ
    0.08
    åı¤ä»£
    0.08
    SYM
    0.08
    UnderTest
    0.08
    äºĶå®ĺ
    0.08
    lest
    0.08
    Activations Density 0.025%

    No Known Activations