© 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. 31802
    Prev
    Next
    INDEX
    Explanations

    attendance and presence

    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
    okin
    -0.09
    iston
    -0.09
    æī¿åıĹ
    -0.09
    ä¸ĵ
    -0.09
    平稳
    -0.09
    ä¼ij
    -0.09
    æĤ²ä¼¤
    -0.09
    bew
    -0.08
     Friedman
    -0.08
    èĹ
    -0.08
    POSITIVE LOGITS
     attendance
    0.16
    æīĵåį¡
    0.14
     Attendance
    0.13
    åĩºå¸Ń
    0.13
    attendance
    0.13
    å¾ĭ
    0.13
    Attendance
    0.13
    æĹ·
    0.12
    åĪ°åľº
    0.12
    缺å¸Ń
    0.12
    Activations Density 0.030%

    No Known Activations