© 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. 2737
    Prev
    Next
    INDEX
    Explanations

    stand-off, tensions, between, East

    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
    çľ¼è§Ĵ
    -0.09
     Walters
    -0.09
    èĢģå¸Ī们
    -0.09
    bulk
    -0.09
    èĨº
    -0.08
     Fay
    -0.08
    ä¸İåħ¶ä»ĸ
    -0.08
    Ctr
    -0.08
    åĢ¡
    -0.08
    并ä¸İ
    -0.08
    POSITIVE LOGITS
    åıĮæĸ¹
    0.15
    åĥµ
    0.12
    丼
    0.11
    åĨ²çªģ
    0.09
     оÑĤноÑĪениÑı
    0.09
    沸
    0.09
    äºĴ
    0.09
    ä¸Ģç¬ij
    0.09
    æij©æĵ¦
    0.09
    ç´§å¼ł
    0.09
    Activations Density 0.115%

    No Known Activations