© 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. 10758
    Prev
    Next
    INDEX
    Explanations

    precise manner/value/mechanism

    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
    sWith
    -0.12
    rev
    -0.10
    ish
    -0.10
    re
    -0.10
    ospace
    -0.09
    lying
    -0.09
    last
    -0.09
    arı
    -0.09
    aras
    -0.09
    ãģĦãģ¾ãģĻ
    -0.09
    POSITIVE LOGITS
    ément
    0.12
     Ñģебе
    0.11
    inct
    0.10
    ely
    0.10
    vely
    0.10
    lessly
    0.10
    _COND
    0.10
    acre
    0.10
    zza
    0.09
     nét
    0.09
    Activations Density 0.012%

    No Known Activations