© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53292
    Prev
    Next
    INDEX
    Explanations

    corner

    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
    ¾
    -0.11
    ively
    -0.11
    æīĭèħķ
    -0.10
    æѤåĪ»
    -0.09
    sic
    -0.09
    æīĭæİĮ
    -0.09
    åħ¥èĤ¡
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    ropa
    -0.08
     chóng
    -0.08
    POSITIVE LOGITS
    åľ°å¸¦
    0.14
    ize
    0.10
    stones
    0.10
    ials
    0.10
    pane
    0.09
    éļħ
    0.09
     lẽ
    0.09
    idon
    0.09
    -corner
    0.09
    Ñİ
    0.09
    Activations Density 0.010%

    No Known Activations