© 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. 21685
    Prev
    Next
    INDEX
    Explanations

    midday to night

    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
    转弯
    -0.09
    èĮ«
    -0.09
    äºĶåĪĨéĴŁ
    -0.09
    æĻļé¤IJ
    -0.09
    æľ«
    -0.09
    otime
    -0.09
    沧
    -0.08
    é»ijå¤ľ
    -0.08
    太ä¹ħ
    -0.08
    _ht
    -0.08
    POSITIVE LOGITS
    çĿģå¼Ģ
    0.09
    å¾ĢåIJİ
    0.09
     pObj
    0.09
    æ·±æ·±åľ°
    0.08
    èĭĵ
    0.08
    çĶµè§Ĩ
    0.08
    باب
    0.08
    ä¸ĵ项è¡ĮåĬ¨
    0.08
     Coding
    0.08
    çĿģ
    0.08
    Activations Density 0.071%

    No Known Activations