© 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. 50444
    Prev
    Next
    INDEX
    Explanations

    company names and websites

    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
    åĽŀ顾
    -0.11
    ascade
    -0.09
    åĿĩ
    -0.09
    è¸ıå®ŀ
    -0.08
    ä¸İæѤ
    -0.08
    诸å¦Ĥ
    -0.08
     Lew
    -0.08
    nable
    -0.08
    Fallback
    -0.08
     Kaw
    -0.07
    POSITIVE LOGITS
    æ¯įåħ¬åı¸
    0.11
    éģĩ
    0.10
    èµ·æĿ¥äºĨ
    0.10
    .com
    0.10
    -like
    0.09
    髦
    0.09
    -Sah
    0.09
    ä¸ĭ鼨
    0.09
    åīį身
    0.09
    èĪIJ
    0.09
    Activations Density 0.078%

    No Known Activations