© 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. 19020
    Prev
    Next
    INDEX
    Explanations

    changes and movement

    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
    èĪĦ
    -0.09
    åıijèµ·
    -0.09
    arella
    -0.09
    窳
    -0.09
    è¿ŁåĪ°
    -0.09
    getter
    -0.09
    å·²ç»ı
    -0.09
    å·²ç»ıæľī
    -0.09
    _constructor
    -0.09
    èĽĭ
    -0.09
    POSITIVE LOGITS
    åıĺåĬ¨
    0.11
    umbo
    0.10
    æį¢äºĨ
    0.10
    çŃīåİŁåĽł
    0.10
    åģļ大
    0.10
    çļĦ带é¢Ĩ
    0.10
    æĸ°çļĦ
    0.09
    åıijçĶŁåıĺåĮĸ
    0.09
    changes
    0.09
     changes
    0.09
    Activations Density 0.355%

    No Known Activations