© 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. 51407
    Prev
    Next
    INDEX
    Explanations

    exercise and healthy habits

    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°l
    -0.09
    å®Ī
    -0.09
    åħ¬æ°ij
    -0.08
    ä¸Ģè§Ĵ
    -0.08
    å¹²äºĭ
    -0.08
    è¿ĩ
    -0.08
    åijĬè¯ī大家
    -0.08
    Si
    -0.08
    ilit
    -0.08
    sf
    -0.07
    POSITIVE LOGITS
    循
    0.11
    秧
    0.11
    æŁĶåĴĮ
    0.10
     gent
    0.10
    ä¼Ľ
    0.10
    åĪĽä¼¤
    0.10
    éĢĤ度
    0.10
    æĹĭå¾ĭ
    0.09
    çļĦ好å¤Ħ
    0.09
    çĸıéĢļ
    0.09
    Activations Density 0.037%

    No Known Activations