© 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. 32609
    Prev
    Next
    INDEX
    Explanations

    can do

    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
    letal
    -0.09
    ä¸ij
    -0.08
    ä¸į对
    -0.08
    ãģİ
    -0.08
    OB
    -0.08
    åIJŃ
    -0.08
     Phụ
    -0.08
    <<(
    -0.08
    .Cursor
    -0.08
    ippet
    -0.08
    POSITIVE LOGITS
    æĶ»åħĭ
    0.11
    æĪĺèĥľ
    0.11
    åĪ¶æľį
    0.10
    åĬ²
    0.10
    å¾ģæľį
    0.10
    æĮ½
    0.10
    åĬŀ好
    0.09
    æīĵçł´
    0.09
    带走
    0.09
     succeed
    0.09
    Activations Density 0.047%

    No Known Activations