© 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. 57362
    Prev
    Next
    INDEX
    Explanations

    tired and weary

    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
    éļľ
    -0.10
    opoly
    -0.09
    bish
    -0.09
    _pll
    -0.09
    /pp
    -0.09
    æįĨç»ij
    -0.09
    æįĨ
    -0.08
    ä½İå»ī
    -0.08
    åľ¨çĶŁæ´»ä¸Ń
    -0.08
    à¹ģà¸Ī
    -0.08
    POSITIVE LOGITS
    çĸ²æĥ«
    0.16
    çĸ²åĬ³
    0.14
    çĸ²
    0.12
    åĢ¦
    0.12
    åĬ³ç´¯
    0.12
    第äºĮ天
    0.11
    åĬ³åĬ¨
    0.11
     fatigue
    0.10
    èĤĮèĤī
    0.10
    çŃĭ
    0.10
    Activations Density 0.058%

    No Known Activations