© 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. 7007
    Prev
    Next
    INDEX
    Explanations

    any noun

    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
    ough
    -0.10
    éĢł
    -0.09
    å¾Īé«ĺåħ´
    -0.08
    SYM
    -0.08
     Bare
    -0.08
    кÑģ
    -0.08
    åĩŃ
    -0.07
    æĹģ
    -0.07
     bast
    -0.07
    åķĨæłĩ
    -0.07
    POSITIVE LOGITS
    Except
    0.12
    åĵªæĢķæĺ¯
    0.11
    _except
    0.11
    çĮ·
    0.10
    è¾ľè´Ł
    0.10
    åĵªæĢķ
    0.09
    以人æ°ij为
    0.09
    OfWeek
    0.09
     Except
    0.09
     سÙĪÙī
    0.09
    Activations Density 0.040%

    No Known Activations