© 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. 57849
    Prev
    Next
    INDEX
    Explanations

    in-law

    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
    åijĺ
    -0.11
    æķ£å¸ĥ
    -0.10
    é«Ģ
    -0.09
    æ½®æµģ
    -0.09
    бÑĢо
    -0.09
    çİĭåŃIJ
    -0.09
    ä¹IJæĦı
    -0.09
    íĭĢ
    -0.09
    æİ©çĽĸ
    -0.09
    æĽ³
    -0.08
    POSITIVE LOGITS
    绶
    0.11
     ll
    0.09
    resh
    0.09
    apy
    0.08
    Globals
    0.08
    idd
    0.08
    (LL
    0.08
    aled
    0.07
    _serializer
    0.07
    -grand
    0.07
    Activations Density 0.002%

    No Known Activations