© 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. 27579
    Prev
    Next
    INDEX
    Explanations

    petty disputes, interpersonal skills/violence

    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
    vable
    -0.10
    oland
    -0.09
    olated
    -0.08
    ry
    -0.08
    æĸ°çļĦä¸Ģå¹´
    -0.08
    åĩºåĩ»
    -0.08
     Lincoln
    -0.08
    аÑĤоÑĢ
    -0.08
    çĤ¯
    -0.08
    ophobic
    -0.08
    POSITIVE LOGITS
    esen
    0.11
    æľºåħ³
    0.11
    ãģªãģĮãĤī
    0.10
    æĹ¥èµ·
    0.10
    RELEASE
    0.10
    еÑģÑĤв
    0.10
    管çIJĨå·¥ä½ľ
    0.10
    鬯
    0.10
    iosa
    0.10
    atures
    0.10
    Activations Density 0.005%

    No Known Activations