© 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. 4284
    Prev
    Next
    INDEX
    Explanations

    if possible

    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
    ýt
    -0.08
    ä½IJ
    -0.08
    brit
    -0.08
    åįĹæĸ¹
    -0.08
    éĻĮçĶŁ
    -0.08
    åĴı
    -0.08
     Shed
    -0.08
    دس
    -0.08
    没åĬŀæ³ķ
    -0.08
     Shen
    -0.07
    POSITIVE LOGITS
    æľīè¿Ļæł·çļĦ
    0.12
     überhaupt
    0.11
    صÙĦا
    0.11
    éĤ£äºº
    0.10
    以人为
    0.10
    çĽ¸å¹²
    0.10
    å¼ķèµ·äºĨ
    0.10
     ÑĢай
    0.09
    å¤©åľ°
    0.09
    acak
    0.09
    Activations Density 0.060%

    No Known Activations