© 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. 34088
    Prev
    Next
    INDEX
    Explanations

    revolution and revolt

    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
    èĨ³
    -0.10
    åķĥ
    -0.10
    å®ļçĤ¹
    -0.09
    诽
    -0.09
     Presence
    -0.09
    ungen
    -0.08
    æĮĩå°ĸ
    -0.08
    _interp
    -0.08
    sink
    -0.08
     Nicholas
    -0.08
    POSITIVE LOGITS
    æľīæĦıä¹ī
    0.13
    èµ·ä¹ī
    0.13
    éĿ©åij½
    0.12
     fight
    0.10
     revolt
    0.10
    åıįæĬĹ
    0.10
    夺
    0.10
    fight
    0.09
    æĸĹäºī
    0.09
    æĦıä¹ī
    0.09
    Activations Density 0.140%

    No Known Activations