© 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. 23796
    Prev
    Next
    INDEX
    Explanations

    almost immediately following numbers

    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
    大æ¦Ĥæĺ¯
    -0.09
    inan
    -0.09
    çĸij
    -0.08
     scalp
    -0.08
    xED
    -0.08
    æŀľ
    -0.08
    itti
    -0.08
     Bent
    -0.08
    大æ¦Ĥ
    -0.08
    åĿļå®ŀ
    -0.08
    POSITIVE LOGITS
    æĹłæķĮ
    0.09
    [[
    0.09
     Rape
    0.09
    å®Įç¾İçļĦ
    0.09
    榨
    0.09
    èŀį为ä¸Ģä½ĵ
    0.09
     entirely
    0.08
    annie
    0.08
    é«ĺçŃī
    0.08
    verständlich
    0.08
    Activations Density 0.083%

    No Known Activations