© 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. 58487
    Prev
    Next
    INDEX
    Explanations

    committed to or commitment of

    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
    .hm
    -0.09
    æ±ĩ
    -0.09
    yme
    -0.08
    èĭ±éĽĦ
    -0.08
    /interface
    -0.08
    åı«æĪij
    -0.08
    çī¹éĤĢ
    -0.08
    åı¯ä»¥æĽ´å¥½
    -0.08
    æĭĴ
    -0.08
    ä½ĵéĩı
    -0.08
    POSITIVE LOGITS
     commitment
    0.19
     commitments
    0.16
     committed
    0.15
     Commit
    0.14
    commit
    0.14
     commit
    0.13
     dedication
    0.13
    committed
    0.12
    .commit
    0.12
    æī¿è¯º
    0.12
    Activations Density 0.039%

    No Known Activations