© 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. 30518
    Prev
    Next
    INDEX
    Explanations

    non-profit

    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
    è¯ĺ
    -0.08
    ÑĢеÑģÑĤ
    -0.08
    åłķ
    -0.08
    vary
    -0.08
    imar
    -0.08
    èĥ½åĬĽå¼º
    -0.08
    ãģ¨ãģĦãģ£ãģ¦
    -0.08
    uffed
    -0.08
    ner
    -0.08
    æĮĤéĴ©
    -0.08
    POSITIVE LOGITS
    Ñĥв
    0.10
    æĹłåģ¿
    0.09
    èĬĿ麻
    0.09
    ubby
    0.09
     Zac
    0.09
    æľ¬å±Ĭ
    0.09
     weblog
    0.09
    uba
    0.09
    dale
    0.09
    _CBC
    0.09
    Activations Density 0.041%

    No Known Activations