© 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. 27516
    Prev
    Next
    INDEX
    Explanations

    stadiums, fields, arenas

    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
    åĽ¢
    -0.10
    æĭ£
    -0.09
     Worship
    -0.09
    .Dispose
    -0.09
    åĪ©äºļ
    -0.08
    æIJŀ
    -0.08
    奢ä¾Ī
    -0.08
    æŃ£å½ĵ
    -0.08
     Balt
    -0.08
     masa
    -0.08
    POSITIVE LOGITS
    _HS
    0.09
    _DX
    0.09
    _STD
    0.09
    .rm
    0.09
    OMB
    0.08
    æĸ°è¥¿
    0.08
    ê°IJ
    0.08
    ç¥ŀå·ŀ
    0.08
    _Surface
    0.08
    ä¸ĩåįĥ
    0.08
    Activations Density 0.030%

    No Known Activations