© 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. 38176
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    æĪijå½ĵæŶ
    -0.10
    ä¸ĭ次
    -0.09
    charAt
    -0.09
    _REMOTE
    -0.09
    åijĬè¯īä»ĸ
    -0.09
     distant
    -0.09
    remote
    -0.09
     пÑĢиÑĩ
    -0.09
    ä¸İæŶ
    -0.09
    æİĴ
    -0.09
    POSITIVE LOGITS
    æľŁ
    0.13
    缮åīį为æŃ¢
    0.11
    以ä¾Ĩ
    0.11
    å¹´éĹ´
    0.10
    ä¸Ģ段æŶéĹ´
    0.10
    以æĿ¥
    0.09
    è¯¥æł¡
    0.09
    建åĨĽ
    0.09
    ä¸ŃåĽ½å¤§éĻĨ
    0.09
    åĭĩ士
    0.09
    Activations Density 0.183%

    No Known Activations