© 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. 33968
    Prev
    Next
    INDEX
    Explanations

    state of

    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
    串èģĶ
    -0.10
    çĵ¢
    -0.09
    æľīéĻIJ
    -0.09
    xfb
    -0.08
    alley
    -0.08
    áŀĦ
    -0.08
    å¼łæī¬
    -0.08
    maf
    -0.08
    åĭ¤
    -0.08
     ÙĨÙĤ
    -0.08
    POSITIVE LOGITS
     affairs
    0.10
    å²Į
    0.09
    åij¨åĽ´çļĦ
    0.09
    çİ°çĬ¶
    0.09
    大å±Ģ
    0.09
    åĨį说
    0.09
    å½¢åĬ¿
    0.09
    ëĶ°
    0.09
    个åĪ«
    0.08
    æĥħåĨµ
    0.08
    Activations Density 0.046%

    No Known Activations