© 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. 29830
    Prev
    Next
    INDEX
    Explanations

    time of day indicators (am/pm)

    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
    ãģĹãģ¾ãģĨ
    -0.11
    å©¿
    -0.10
    缤纷
    -0.10
    TING
    -0.09
    sume
    -0.09
    esch
    -0.09
    人å±ħ
    -0.09
    代表大ä¼ļ
    -0.09
    fried
    -0.09
    设计å¸Ī
    -0.09
    POSITIVE LOGITS
     Ñĩа
    0.10
    glas
    0.09
    stit
    0.09
    wap
    0.08
    upe
    0.08
    illes
    0.08
    æĥ©
    0.08
    avra
    0.08
    uÃŃ
    0.07
    äºĭåIJİ
    0.07
    Activations Density 0.014%

    No Known Activations