© 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. 61622
    Prev
    Next
    INDEX
    Explanations

    puncture and insertion

    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
    移
    -0.08
    æĸ§
    -0.08
    à¸Ħาร
    -0.08
    SetValue
    -0.08
    IZE
    -0.08
    EQ
    -0.08
    尺度
    -0.08
    anter
    -0.08
    exter
    -0.08
     hal
    -0.08
    POSITIVE LOGITS
    æīİ
    0.11
    uring
    0.09
    æĻ´
    0.09
    á»Ĺ
    0.09
     jab
    0.09
     Intr
    0.09
    ä¹į
    0.09
     punct
    0.09
    æľ¬ç½ij
    0.08
    æįħ
    0.08
    Activations Density 0.046%

    No Known Activations