© 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. 4417
    Prev
    Next
    INDEX
    Explanations

    moving locations

    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
    åĪĩå®ŀ
    -0.09
    .gov
    -0.09
    åĪĩ
    -0.08
    åijķ
    -0.08
    è¢ĭåŃIJ
    -0.07
    insky
    -0.07
    spot
    -0.07
    æĮİ
    -0.07
    çĤ¹æ»´
    -0.07
    ochen
    -0.07
    POSITIVE LOGITS
    æĿ¥åĪ°
    0.11
    éķĴ
    0.10
    yon
    0.10
    çİij
    0.10
    acom
    0.10
    å®ļå±ħ
    0.09
    å±ħä½ı
    0.09
    Sdk
    0.09
    ä¸ĢçĽ´åľ¨
    0.09
    åıijå±ķ空éĹ´
    0.09
    Activations Density 0.178%

    No Known Activations