© 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. 63607
    Prev
    Next
    INDEX
    Explanations

    know better 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
    -ng
    -0.11
    羣æŃ£
    -0.11
     peg
    -0.09
    蹩
    -0.09
    åħ·æľīä¸Ģå®ļ
    -0.09
    peg
    -0.09
    èµ°å¾Ĺ
    -0.09
     доволÑĮ
    -0.09
    æı´
    -0.09
    æľīä¸Ģå®ļ
    -0.09
    POSITIVE LOGITS
    è¦ģä¸įè¦ģ
    0.09
    çĶµç£ģ
    0.09
    çĽ²çĽ®
    0.08
     sadd
    0.08
    èĽŁ
    0.08
    chai
    0.08
    odiac
    0.08
    侪
    0.08
    lya
    0.08
    LY
    0.08
    Activations Density 0.006%

    No Known Activations