© 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. 56575
    Prev
    Next
    INDEX
    Explanations

    word -related

    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
    åľ¨çİ°åľº
    -0.10
    å¿ĥ缮ä¸Ń
    -0.10
    认为
    -0.10
    æīĢåľ¨åľ°
    -0.10
     владелÑĮÑĨ
    -0.09
    åĮĸè¿Ľç¨ĭ
    -0.09
    æĺ¯ä¸ºäºĨ
    -0.09
    igua
    -0.09
    æŁIJç§įç¨ĭ度
    -0.09
    ç½ijä¸Ĭ
    -0.09
    POSITIVE LOGITS
    äºĭå®ľ
    0.11
    gers
    0.10
     matters
    0.09
    ä»ĸå°±
    0.09
    Executable
    0.08
    èĢĮåľ¨
    0.08
     Matters
    0.08
    -Oct
    0.08
    该éĻ¢
    0.08
     Penn
    0.08
    Activations Density 0.063%

    No Known Activations