© 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. 36719
    Prev
    Next
    INDEX
    Explanations

    restraining order or ban

    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
     cul
    -0.10
    åĽ½éĺ²
    -0.10
    æĹłä¸į
    -0.09
    çīºçī²
    -0.09
    gate
    -0.09
    ãĤ²
    -0.09
    labs
    -0.09
    preload
    -0.08
    èį©
    -0.08
    å¿ĥçĸ¼
    -0.08
    POSITIVE LOGITS
    解éĻ¤
    0.11
    ament
    0.09
    åħŃåIJĪ
    0.08
     Lift
    0.08
    å»¶æľŁ
    0.08
    ä¸ĩåįĥ
    0.08
    aminer
    0.08
     mor
    0.08
     Rai
    0.08
    èįª
    0.08
    Activations Density 0.070%

    No Known Activations