© 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. 10234
    Prev
    Next
    INDEX
    Explanations

    food coloring, whisky, sauce

    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
    éĴ¥åĮĻ
    -0.09
    èĸ°
    -0.09
    æĴij
    -0.09
    离ä¸įå¼Ģ
    -0.09
    çIJ¬
    -0.09
    丰ç¡ķ
    -0.08
    roz
    -0.08
    æĴIJ
    -0.08
     infl
    -0.08
    çŃ¹å¤ĩ
    -0.08
    POSITIVE LOGITS
    åij½
    0.09
    Leaks
    0.09
    QueryString
    0.08
     Salman
    0.08
    gart
    0.08
    dra
    0.08
    缶
    0.08
    鸥
    0.08
    顺
    0.08
    év
    0.08
    Activations Density 0.005%

    No Known Activations