© 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. 57515
    Prev
    Next
    INDEX
    Explanations

    may you share or make

    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
    éģij
    -0.10
    è¿Ļä¸ĢçĤ¹
    -0.10
    ãĤ¨ãĥįãĥ«
    -0.10
    è¿Ļå¥Ĺ
    -0.10
    åģļåĪ°äºĨ
    -0.10
    ä»ĸä¹Ł
    -0.10
    åĪ°æŶåĢĻ
    -0.10
    罡
    -0.09
    ä½ıäºĨ
    -0.09
    åı¯è°ĵæĺ¯
    -0.09
    POSITIVE LOGITS
    ãģĿãĤĤãģĿãĤĤ
    0.11
     вообÑīе
    0.08
    antha
    0.08
    iding
    0.07
    HAL
    0.07
    _LL
    0.07
    iden
    0.07
     importantly
    0.07
    (uuid
    0.07
    æĪ¿ä¸ľ
    0.07
    Activations Density 0.426%

    No Known Activations