© 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. 56149
    Prev
    Next
    INDEX
    Explanations

    match or matched

    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
    ave
    -0.10
    éĢł
    -0.10
     Holden
    -0.09
    è¯ķ
    -0.09
    geme
    -0.08
    ainment
    -0.08
    å¾ĩ
    -0.08
     Massive
    -0.08
    cia
    -0.08
    STE
    -0.08
    POSITIVE LOGITS
    .Match
    0.11
    (match
    0.10
    对人ä½ĵ
    0.10
    ä¼łç»Łäº§ä¸ļ
    0.10
     matched
    0.09
    è´¨æĦŁ
    0.09
     Match
    0.09
    穷人
    0.09
    åĮ¹éħį
    0.09
    loat
    0.09
    Activations Density 0.054%

    No Known Activations