© 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. 53648
    Prev
    Next
    INDEX
    Explanations

    electrical connection points or terminals

    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
    åı£å¾Ħ
    -0.09
    otte
    -0.09
    unta
    -0.09
    à¸Ńà¸Ķ
    -0.09
    çĤ¹åĩ»æŁ¥çľĭ
    -0.09
     flo
    -0.09
    nü
    -0.09
    ERGY
    -0.09
    flo
    -0.09
    åħ¨æµģç¨ĭ
    -0.08
    POSITIVE LOGITS
    秣
    0.09
    ild
    0.09
    常德
    0.08
    èķĬ
    0.08
    ä¹ĭéĹ´
    0.08
    æĻ¦
    0.08
    奢åįİ
    0.08
    åĪĨ离
    0.08
     rested
    0.08
    纪
    0.08
    Activations Density 0.150%

    No Known Activations