© 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. 61255
    Prev
    Next
    INDEX
    Explanations

    commitment to

    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
    Unity
    -0.09
    æĶ¹åĪ¶
    -0.09
    端æŃ£
    -0.08
    ä¸įå¼Ģ
    -0.08
    åºı
    -0.08
    _inst
    -0.08
    åĶĨ
    -0.08
    宽æĿ¾
    -0.08
    å¾ģ
    -0.08
    åĩºå±Ģ
    -0.08
    POSITIVE LOGITS
    æī¿è¯º
    0.23
     commitments
    0.22
     commitment
    0.22
     Commit
    0.19
     commit
    0.18
    commit
    0.18
     committing
    0.17
     commits
    0.16
     committed
    0.16
    (commit
    0.15
    Activations Density 0.059%

    No Known Activations