© 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. 18605
    Prev
    Next
    INDEX
    Explanations

    Premier League

    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
    æ¢ĵ
    -0.11
    her
    -0.09
    oca
    -0.09
    ÙĪØ·
    -0.09
    磨æįŁ
    -0.08
    hes
    -0.08
    omba
    -0.08
    ÑĭÑĤа
    -0.08
    ÙĨز
    -0.08
    itting
    -0.08
    POSITIVE LOGITS
    chaft
    0.12
    让å®ĥ
    0.11
    ships
    0.10
    diamond
    0.09
    ement
    0.09
    istory
    0.09
     GC
    0.08
    ship
    0.08
    åŀĭä¼ģä¸ļ
    0.08
    ized
    0.08
    Activations Density 0.009%

    No Known Activations