© 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. 22717
    Prev
    Next
    INDEX
    Explanations

    involved or managing professions

    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
    ym
    -0.09
    èĮ¬
    -0.08
     наб
    -0.08
    cue
    -0.08
    为é¦ĸçļĦ
    -0.07
    èIJİ
    -0.07
    å½ĵåľ°äºº
    -0.07
     Dur
    -0.07
    ç¥
    -0.07
     Greene
    -0.07
    POSITIVE LOGITS
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.13
    æĪIJè´¥
    0.11
    æīĵ交éģĵ
    0.11
    åıĹå½±åĵį
    0.10
    æ¶īåıĬ
    0.09
    ä½ĵåĪ¶æĶ¹éĿ©
    0.09
    å¿ħä¸įåı¯å°ij
    0.09
    è¦ģä¹Ī
    0.09
    ä¸Ĭä¸ĭ游
    0.09
    æĪĸå¤ļæĪĸå°ij
    0.09
    Activations Density 0.093%

    No Known Activations