© 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. 4299
    Prev
    Next
    INDEX
    Explanations

    in this together

    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
    éĻ¤æѤ
    -0.09
    æĬ¬èµ·
    -0.08
    åĬłä¹ĭ
    -0.08
    éĢīæĭ
    -0.08
    IPA
    -0.08
    ä¸įä¿¡
    -0.08
     scar
    -0.08
    æĥĭ
    -0.08
    _IW
    -0.08
     postings
    -0.08
    POSITIVE LOGITS
     tou
    0.09
    éľ²
    0.09
    æļĤåģľ
    0.08
    è°²
    0.08
    дол
    0.08
    ä¸įä»ħè¦ģ
    0.08
    èµ¢
    0.08
    .elem
    0.08
    æľīäºĽ
    0.08
     prm
    0.08
    Activations Density 0.023%

    No Known Activations