© 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. 51393
    Prev
    Next
    INDEX
    Explanations

    irming or irmed

    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
    iders
    -0.09
     Falk
    -0.09
    imest
    -0.08
    ä»Ģä¹Īæł·
    -0.08
    odd
    -0.08
    ough
    -0.08
    grass
    -0.08
    girl
    -0.08
    è¯Ŀ说
    -0.08
    elper
    -0.08
    POSITIVE LOGITS
    atively
    0.14
    atory
    0.12
    ament
    0.10
    ative
    0.10
    ments
    0.10
    ¹
    0.09
    ä¸Ģä¸ĭ
    0.09
    ä¸įäºĨ
    0.09
    icas
    0.09
    atives
    0.09
    Activations Density 0.006%

    No Known Activations