© 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. 50461
    Prev
    Next
    INDEX
    Explanations

    shows or indicates

    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
     Lam
    -0.08
    åĢį
    -0.08
    ç¢İ
    -0.08
    æ¦ķ
    -0.08
     Wol
    -0.08
     Curry
    -0.08
    åīij
    -0.08
    á»ĩ
    -0.08
     Ñĥни
    -0.08
     jet
    -0.07
    POSITIVE LOGITS
    說æĺİ
    0.11
    说æĺİ
    0.11
     ske
    0.11
    ä½ĵçİ°äºĨ
    0.10
    èĢģ大
    0.10
    黥
    0.10
     Chip
    0.09
    uler
    0.09
    表æĺİ
    0.09
    è¯ģæĺİ
    0.09
    Activations Density 0.074%

    No Known Activations