© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19389
    Prev
    Next
    INDEX
    Explanations

    governor names and titles

    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
     Rodney
    -0.09
    è¿ĺ以为
    -0.09
    æľ¬éĩij
    -0.09
    è°¨æħİ
    -0.09
    è¯Ľ
    -0.09
    é¢ĩ
    -0.09
    æµ·åĨĽ
    -0.09
    ddit
    -0.08
    以为
    -0.08
    _timing
    -0.08
    POSITIVE LOGITS
    èĢģçĪ·
    0.10
    ëĭĺ
    0.10
    -widgets
    0.09
    ç»°
    0.09
    _gem
    0.09
    çľģæĶ¿åºľ
    0.09
    åĮºåŁŁæĢ§
    0.09
     governors
    0.09
    çѱ
    0.09
    state
    0.09
    Activations Density 0.017%

    No Known Activations