© 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. 22696
    Prev
    Next
    INDEX
    Explanations

    quantities of time or items

    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
    ä¸Ģæŀļ
    -0.10
    æľºåĬ¨
    -0.10
    aines
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    罡
    -0.09
    ounds
    -0.09
    å¸ĥæĭī
    -0.09
    çŀ½
    -0.09
    çļĦéŃħåĬĽ
    -0.09
    ä¸ĢåĪ»
    -0.09
    POSITIVE LOGITS
    éĥ½éĿŀ常
    0.09
    duino
    0.08
    MENT
    0.08
     alike
    0.08
    ç¬ĥ
    0.08
    ish
    0.08
    venir
    0.08
    åIJįä¹ī
    0.08
    uchi
    0.07
    缸继
    0.07
    Activations Density 0.014%

    No Known Activations