© 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. 61140
    Prev
    Next
    INDEX
    Explanations

    tempted, inclined, easy

    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
    ä¸İæŶ
    -0.09
    èĢ½è¯¯
    -0.09
    ç¡Ŀ
    -0.09
    arb
    -0.08
    轸
    -0.08
     Clause
    -0.08
    éĴ°
    -0.08
     educated
    -0.08
     deb
    -0.08
    alker
    -0.08
    POSITIVE LOGITS
     temptation
    0.17
     tempted
    0.16
     tempting
    0.14
    åĢ¾åIJijäºİ
    0.12
     tendency
    0.12
    诱æĥij
    0.12
    åĨ²åĬ¨
    0.12
     tend
    0.12
    ä¼ļè§īå¾Ĺ
    0.12
    tempt
    0.12
    Activations Density 0.039%

    No Known Activations