© 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. 3957
    Prev
    Next
    INDEX
    Explanations

    fistula or perforation

    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
    å³°
    -0.11
    cona
    -0.09
    LING
    -0.08
    对ä»ĸ们
    -0.08
     shadows
    -0.08
    åģ¶
    -0.08
    æ®ĭ
    -0.08
    _READONLY
    -0.08
    大大å°ı
    -0.08
    åħ±äº«
    -0.08
    POSITIVE LOGITS
    沿线
    0.10
    åŀ«
    0.10
    æ¸Į
    0.09
    æ½ľèĥ½
    0.09
    çł´è£Ĥ
    0.09
    ivid
    0.09
     Redistributions
    0.09
    ãĥĽ
    0.09
    çĥ«
    0.09
    bench
    0.09
    Activations Density 0.218%

    No Known Activations