© 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. 26547
    Prev
    Next
    INDEX
    Explanations

    less than or more than

    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
    æ³ħ
    -0.10
     small
    -0.10
    OMB
    -0.09
    å°ıå·§
    -0.09
    nees
    -0.09
    å°ıåŃIJ
    -0.09
     Kore
    -0.09
    絾
    -0.09
    lean
    -0.09
     EXPORT
    -0.08
    POSITIVE LOGITS
     full
    0.11
     Full
    0.11
    满
    0.10
    å®Įæķ´
    0.10
    满åĪĨ
    0.10
    å®Įæķ´çļĦ
    0.10
    èĤ¥
    0.09
    åħ¨éĿ¢æİ¨è¿Ľ
    0.09
     FULL
    0.09
    æľīçļĦ人
    0.09
    Activations Density 0.059%

    No Known Activations