© 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. 31473
    Prev
    Next
    INDEX
    Explanations

    age ranges

    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¸Ģå¹´ä¸Ģ度
    -0.10
    ä¹ĭ举
    -0.08
    ä¹ĭéģĵ
    -0.08
    åįłåľ°
    -0.08
    hy
    -0.08
    åı©
    -0.08
    訴
    -0.08
    åIJĪ
    -0.08
     пока
    -0.08
    士
    -0.08
    POSITIVE LOGITS
    åIJİæľŁ
    0.16
     adulthood
    0.13
    æĻļå¹´
    0.13
    æĻļæľŁ
    0.10
     middle
    0.10
    é»Ħéĩij
    0.10
     adolescence
    0.10
    é»Ħæĺı
    0.10
    åīįæľŁ
    0.10
    ä¸ŃæľŁ
    0.09
    Activations Density 0.156%

    No Known Activations