© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9618
    Prev
    Next
    INDEX
    Explanations

    playoff spots or positions

    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
    åĬŀæ³ķ
    -0.09
    æĥ³æī¾
    -0.09
    é¦ĸ家
    -0.08
    ä¹ĭå¤ľ
    -0.08
    zed
    -0.08
    oland
    -0.08
    ой
    -0.08
    辦æ³ķ
    -0.08
    é²Ń
    -0.08
    ivi
    -0.08
    POSITIVE LOGITS
    processors
    0.10
    åĦ¿
    0.10
    æĭ¿åĩºæĿ¥
    0.09
    åĤ¬
    0.08
    ential
    0.08
    eway
    0.08
    mites
    0.08
    æĬł
    0.08
    æµģ失
    0.08
    ãģĸ
    0.08
    Activations Density 0.017%

    No Known Activations