© 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. 34665
    Prev
    Next
    INDEX
    Explanations

    super followed by adjective

    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¸Ģä½ĵ
    -0.10
    idable
    -0.09
    æĽ´å¥½åľ°
    -0.09
    å½ĵçĦ¶
    -0.09
    足
    -0.08
    ä¸Ģ次æĢ§
    -0.08
     cánh
    -0.08
     ÑģамÑĭе
    -0.08
    çĮĽçĦ¶
    -0.08
    çĮĽåľ°
    -0.08
    POSITIVE LOGITS
    æŃ¤äºº
    0.10
    æľīä¿¡å¿ĥ
    0.10
    ä½İä¸ĭ
    0.10
    æĬķåħ¥åĪ°
    0.09
    -low
    0.09
    æħİéĩį
    0.09
     CLOSE
    0.09
    æľīæĦıæĢĿ
    0.09
    没æľīåĬŀæ³ķ
    0.09
     vit
    0.09
    Activations Density 0.009%

    No Known Activations