© 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. 32432
    Prev
    Next
    INDEX
    Explanations

    football competition terms

    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
    çľģæķĻèĤ²åİħ
    -0.11
    vern
    -0.09
    å¾·èĤ²
    -0.09
    äºĨå¤ļå°ij
    -0.09
    举é£İ
    -0.09
    çĦ¶æĺ¯
    -0.09
     долж
    -0.09
    å°±é¤IJ
    -0.09
    æī¾å·¥ä½ľ
    -0.09
    reds
    -0.09
    POSITIVE LOGITS
    éħį
    0.08
    åĽ½éĻħå¸Ĥåľº
    0.08
    åİĨåı²ä¸Ĭ
    0.08
    hib
    0.08
    hic
    0.08
    æĭŃ
    0.08
     Vas
    0.08
     Marvin
    0.08
    antor
    0.07
     McDon
    0.07
    Activations Density 0.161%

    No Known Activations