© 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. 34427
    Prev
    Next
    INDEX
    Explanations

    forests and timber

    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
    rid
    -0.10
    ç½ijç«Ļ建设
    -0.09
    失æķĪ
    -0.09
    ertz
    -0.09
    èĿ¶
    -0.09
    èĤļ
    -0.08
    ç¥ĵ
    -0.08
    åı¸
    -0.08
    åĬŁå¤«
    -0.08
    工夫
    -0.08
    POSITIVE LOGITS
    森æŀĹ
    0.17
     forest
    0.15
     Forest
    0.14
    æŀĹ
    0.13
    forest
    0.13
     forests
    0.13
    ä¼IJ
    0.12
    æŀĹä¸ļ
    0.12
    Forest
    0.11
    æłij
    0.11
    Activations Density 0.136%

    No Known Activations