© 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. 35367
    Prev
    Next
    INDEX
    Explanations

    computing systems and power

    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
    æķĿ
    -0.09
    ä¸Ńæĸĩ
    -0.08
     accom
    -0.08
    éķ¿ä¹ħ
    -0.08
    olian
    -0.08
    éĩįè¦ģåĨħ容
    -0.08
    /forms
    -0.08
     PAN
    -0.08
    pane
    -0.08
    è¾İ
    -0.08
    POSITIVE LOGITS
     computers
    0.15
    ä¸Ģåı°
    0.14
    çĶµèĦij
    0.14
    计ç®Ĺæľº
    0.13
     компÑĮÑİÑĤеÑĢ
    0.12
     computer
    0.12
    鼻èħ¦
    0.12
     Computers
    0.11
     ì»´íĵ¨íĦ°
    0.11
     powerful
    0.11
    Activations Density 0.122%

    No Known Activations