© 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. 3328
    Prev
    Next
    INDEX
    Explanations

    board games

    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
    çIJĥ
    -0.10
     ifdef
    -0.09
    èĮ«èĮ«
    -0.09
    mund
    -0.09
    WithIdentifier
    -0.09
    èģĭ
    -0.08
    æĥłåıĬ
    -0.08
    å¿«æīĭ
    -0.08
    cut
    -0.08
    å¯Ħ
    -0.08
    POSITIVE LOGITS
    emat
    0.09
    æīĵæĬĺ
    0.09
    èŀºæĹĭ
    0.09
    æİ·
    0.09
    åıĮèĦļ
    0.08
    drag
    0.08
    缮ãģ«
    0.08
    çļĦåľ°
    0.08
     Overs
    0.08
     moveTo
    0.08
    Activations Density 0.039%

    No Known Activations