© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    functional programming

    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
    ä»ĸå¦Ī
    -0.09
    éĺĨ
    -0.08
    交代
    -0.08
    è¯Ŀè¯ŃæĿĥ
    -0.08
    油价
    -0.08
    ÑĩÑĥ
    -0.08
    \Configuration
    -0.08
    _OVERRIDE
    -0.08
    ditor
    -0.08
     Seks
    -0.08
    POSITIVE LOGITS
     Haskell
    0.09
    Monad
    0.09
     Reid
    0.08
    çİ
    0.08
     Curry
    0.08
    å°¾
    0.07
    cljs
    0.07
     Hind
    0.07
    Ø®ÙĦÙģ
    0.07
     Monad
    0.07
    Activations Density 1.017%

    No Known Activations