© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 53075
    Prev
    Next
    INDEX
    Explanations

    fishing or hunting contexts

    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
    æ½ĩæ´Ĵ
    -0.10
    åIJĮå¿Ĺ
    -0.09
    åĪĽæĸ°åıijå±ķ
    -0.09
     autoc
    -0.09
    éļĻ
    -0.08
    å°¼äºļ
    -0.08
    åıijå±ķ模å¼ı
    -0.08
    å¸ĥç½®
    -0.08
    å°±å¤ŁäºĨ
    -0.08
    æķķ
    -0.08
    POSITIVE LOGITS
    abin
    0.09
     оÑĤзÑĭв
    0.09
    gy
    0.09
    åĿ¨
    0.09
    aban
    0.09
    åı¯è§Ĩ
    0.09
    åIJŀ
    0.08
    awa
    0.08
    æĻĴ
    0.08
    åĴ¨
    0.08
    Activations Density 0.014%

    No Known Activations