© 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. 61344
    Prev
    Next
    INDEX
    Explanations

    months

    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
    oller
    -0.11
    éĹ³
    -0.11
     reconc
    -0.10
    鹬
    -0.10
    otti
    -0.09
    é³Ĺ
    -0.09
    导读
    -0.09
    á»ĩu
    -0.09
    ç¤ģ
    -0.09
    regor
    -0.09
    POSITIVE LOGITS
    åºľ
    0.09
    iano
    0.08
    ton
    0.08
     aire
    0.08
     mixer
    0.08
    ä¿Ŀå®ī
    0.08
    cly
    0.08
    SELL
    0.07
    ANO
    0.07
    YG
    0.07
    Activations Density 0.031%

    No Known Activations