© 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. 38606
    Prev
    Next
    INDEX
    Explanations

    cutting half, angle, portion, whites

    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
    REW
    -0.09
    å¿ĥå¢ĥ
    -0.09
    è¸Ĭè·ĥ
    -0.09
    åĨ¶
    -0.09
    ä¸Ģè¡Į
    -0.08
    å¿Ļ
    -0.08
    大éĺŁ
    -0.08
    没èĥ½
    -0.08
    enna
    -0.08
    éĤ£ä½į
    -0.08
    POSITIVE LOGITS
    壳
    0.11
    è£Ĥ
    0.11
    åīĸ
    0.10
    æµij
    0.10
    æĸĩåĮĸèīºæľ¯
    0.09
    éĺ²èħIJ
    0.09
    umbo
    0.09
    人èĦ¸è¯ĨåĪ«
    0.08
    èħĶ
    0.08
    leur
    0.08
    Activations Density 0.016%

    No Known Activations