© 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. 27536
    Prev
    Next
    INDEX
    Explanations

    saying or adding

    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
    令人
    -0.10
    使人
    -0.09
     Glover
    -0.09
    æ¥Ķ
    -0.09
    æĿĢæīĭ
    -0.09
    ugen
    -0.09
    æijĪ
    -0.08
    让人
    -0.08
    好åIJ§
    -0.08
     fro
    -0.08
    POSITIVE LOGITS
    说æĪij
    0.13
    æĮĩåĩº
    0.12
    è§īå¾Ĺ
    0.11
    认为
    0.11
    强è°ĥ
    0.11
    说æĺ¯
    0.10
    说
    0.10
     saying
    0.09
    çĿĢéĩį
    0.09
    ROP
    0.09
    Activations Density 0.042%

    No Known Activations