© 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. 6834
    Prev
    Next
    INDEX
    Explanations

    clock and time-related contexts

    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
    ksen
    -0.10
    oge
    -0.09
    Ñģен
    -0.09
    èµĥ
    -0.09
    ÑģÑı
    -0.09
     dụng
    -0.09
    /close
    -0.09
    outu
    -0.09
    ccount
    -0.08
    iale
    -0.08
    POSITIVE LOGITS
    ×ķת
    0.12
    ingly
    0.12
    _gettime
    0.11
    tower
    0.11
    é¦Ĺ
    0.10
    æĥº
    0.09
    ç¢İçīĩ
    0.09
    pedia
    0.09
    edList
    0.09
    ta
    0.09
    Activations Density 0.013%

    No Known Activations