© 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. 62882
    Prev
    Next
    INDEX
    Explanations

    admitted to hospital

    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
    aggio
    -0.10
    åIJ¬åIJ¬
    -0.09
    uls
    -0.09
    ertz
    -0.08
    dim
    -0.08
    dat
    -0.08
    积æ·Ģ
    -0.08
    ectors
    -0.08
    .toObject
    -0.08
    rone
    -0.07
    POSITIVE LOGITS
    è¿ŀå¤ľ
    0.11
    履约
    0.10
    éĻĦè¿ijçļĦ
    0.10
    ÑĦÑĤ
    0.10
    é¡¿
    0.09
    isel
    0.09
    ereg
    0.09
    Unchecked
    0.09
    å½ĵåľº
    0.09
    é³³
    0.08
    Activations Density 0.021%

    No Known Activations