© 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. 4894
    Prev
    Next
    INDEX
    Explanations

    strong X (quality/attribute)

    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
    å¤ļå°ij
    -0.09
    elite
    -0.09
    anz
    -0.08
    ä½ľåĩº
    -0.08
    é¦Ļ
    -0.08
    åģľæŃ¢
    -0.08
    alto
    -0.08
    åIJĽ
    -0.08
    Exclusive
    -0.08
    å¢ŀå¹ħ
    -0.07
    POSITIVE LOGITS
    enko
    0.11
    åĿļå®ŀçļĦ
    0.10
    æ¸Ĭ
    0.10
    éĢļ讯åijĺ
    0.10
    ensi
    0.10
    篮
    0.09
    ened
    0.09
    éļIJç§ģ
    0.09
    oted
    0.09
    ä¸į解
    0.09
    Activations Density 0.017%

    No Known Activations