© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9290
    Prev
    Next
    INDEX
    Explanations

    with [LLVM or Class or block or Alias or chained]

    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
    asz
    -0.10
    äºİæĺ¯æĪij
    -0.09
    éĹªåħī
    -0.09
    AZE
    -0.09
    izr
    -0.08
    åįĥåı¤
    -0.08
    çļĦä¸Ģéĥ¨åĪĨ
    -0.08
    vang
    -0.08
    çªģåĽ´
    -0.08
    Trou
    -0.08
    POSITIVE LOGITS
    drawable
    0.09
    lac
    0.09
    stood
    0.09
    standing
    0.09
    craft
    0.09
    imer
    0.09
    еÑĩение
    0.09
    n
    0.08
    stands
    0.08
    åĢŁåĬ©
    0.08
    Activations Density 0.117%

    No Known Activations