© 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. 37899
    Prev
    Next
    INDEX
    Explanations

    montage, hodgepodge, bergs, tape, histogram

    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°¨æħİ
    -0.09
    ization
    -0.09
    loc
    -0.09
    bies
    -0.09
    lien
    -0.09
    itarian
    -0.09
    ç¦Ģ
    -0.09
    низ
    -0.09
    avigation
    -0.08
    ckett
    -0.08
    POSITIVE LOGITS
    æĸ°ä¸ŃåĽ½
    0.09
    é¸Ń
    0.09
    jur
    0.09
    iras
    0.09
    åĮ®
    0.09
    åĩºèº«
    0.09
    geries
    0.08
    鹫
    0.08
    ìĬ¹
    0.08
    oppers
    0.08
    Activations Density 0.004%

    No Known Activations