© 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. 17562
    Prev
    Next
    INDEX
    Explanations

    variable discussions

    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
    ening
    -0.11
    ðŁı»
    -0.11
    iture
    -0.10
    ØŃØ©
    -0.10
    ned
    -0.09
    uite
    -0.09
    ×ķת
    -0.09
    born
    -0.09
    好åIJĹ
    -0.09
    eds
    -0.09
    POSITIVE LOGITS
    :variables
    0.11
    iants
    0.10
     thả
    0.10
    ç¯Ĩ
    0.09
    ÑģÑı
    0.09
    æ³¢çī¹
    0.09
    ENDED
    0.09
    mente
    0.09
    å·½
    0.09
    меÑĤ
    0.09
    Activations Density 0.080%

    No Known Activations