© 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. 7224
    Prev
    Next
    INDEX
    Explanations

    progress updates

    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¸ij
    -0.11
    循
    -0.09
    ä¸Ģ声
    -0.09
     Swiss
    -0.08
     somehow
    -0.08
    ä¹Łä¸įåı¯èĥ½
    -0.08
    身为
    -0.08
    ç«¥
    -0.08
    æľĢåIJİä¸Ģ个
    -0.08
    à¤Ī
    -0.08
    POSITIVE LOGITS
    å¾¼
    0.10
    饮çĶ¨æ°´
    0.10
    ä¸İåıijå±ķ
    0.09
    etting
    0.09
    å®ľå±ħ
    0.08
    ãģĬãģĭ
    0.08
    é¢Ĩ
    0.08
    _TA
    0.08
    碳éħ¸
    0.08
     hạng
    0.08
    Activations Density 0.002%

    No Known Activations