© 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. 7213
    Prev
    Next
    INDEX
    Explanations

    see or hear

    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
    æī¾åĩº
    -0.10
    mans
    -0.09
    ÑĢиÑģ
    -0.09
    ayette
    -0.09
    ologies
    -0.08
    èĥĥåı£
    -0.08
    _LS
    -0.08
    ypad
    -0.08
    ocks
    -0.08
    obia
    -0.08
    POSITIVE LOGITS
    èijĹåIJį
    0.11
    æľīåIJį
    0.10
    èħĨ
    0.10
    наÑĤ
    0.10
    æĭ±
    0.09
    æľīåIJįçļĦ
    0.09
     вÑĭполнен
    0.09
    çŁ¥åIJį
    0.09
    פ×ķר
    0.09
    é£İéĩĩ
    0.08
    Activations Density 0.028%

    No Known Activations