© 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. 4546
    Prev
    Next
    INDEX
    Explanations

    getaway or escape

    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
    ãģĹãģ¾ãģĨ
    -0.10
    èĨĽ
    -0.09
    ä¸į满
    -0.09
    .TryParse
    -0.09
    ä¸įå¾Ĺ转载
    -0.09
    ument
    -0.08
    饱满
    -0.08
    ired
    -0.08
    éªĪ
    -0.08
    pth
    -0.08
    POSITIVE LOGITS
    åĴª
    0.10
    اخ
    0.09
    åłij
    0.09
    èµİ
    0.09
    è§
    0.09
    صØŃ
    0.09
    æ¶Īæŀģ
    0.08
    躲
    0.08
     пÑĢедназнаÑĩен
    0.08
    -away
    0.08
    Activations Density 0.006%

    No Known Activations