© 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. 6696
    Prev
    Next
    INDEX
    Explanations

    the [noun/adjective]

    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
    ember
    -0.09
    à¸Ķา
    -0.08
    VERSE
    -0.08
     пÑĢакÑĤиÑĩеÑģки
    -0.08
    erie
    -0.08
    äm
    -0.08
    建ç«ĭèµ·
    -0.08
    .dd
    -0.08
    _minor
    -0.08
     Manhattan
    -0.08
    POSITIVE LOGITS
    æľĢæĸ°çļĦ
    0.10
    åĬ©éķ¿
    0.09
    æı´
    0.09
    ç±»åŀĭçļĦ
    0.09
     ropes
    0.09
    æµİ
    0.09
    æĹĹèĪ°
    0.08
    latest
    0.08
    对çŃĸ
    0.08
    iped
    0.08
    Activations Density 0.179%

    No Known Activations