© 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. 1430
    Prev
    Next
    INDEX
    Explanations

    specific characteristics or reasons

    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
    èĭ¥å¹²
    -0.09
    åıĪæľī
    -0.09
    iras
    -0.08
    æĸ¹åı¯
    -0.08
    æŁIJäºĽ
    -0.08
    Tank
    -0.08
     Prem
    -0.08
    uc
    -0.08
    å¾Īæľī
    -0.08
    æĴ¼
    -0.08
    POSITIVE LOGITS
    è¿Ļæĺ¯ä¸Ģ个
    0.10
    æľŁå¾ħ
    0.10
    _expect
    0.10
    ä»Ģä¹ĪåİŁåĽł
    0.10
    æijĨåľ¨
    0.10
    ä¸ĢåıĮ
    0.10
    å½»
    0.09
    ланд
    0.09
    éĩįéĩį
    0.09
     except
    0.09
    Activations Density 0.036%

    No Known Activations