© 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. 19199
    Prev
    Next
    INDEX
    Explanations

    certainly X

    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
    ä»Ģä¹Īåij¢
    -0.10
    鼩
    -0.09
    blink
    -0.09
    sters
    -0.09
    åIJĽ
    -0.08
    è¯Ģ
    -0.08
    ç¡ķ
    -0.08
    å¾Īç®Ģåįķ
    -0.08
    DIR
    -0.08
    æĭĴä¸į
    -0.07
    POSITIVE LOGITS
    æĺ¯ä¸Ģéĥ¨
    0.10
    otent
    0.09
    że
    0.09
     certainly
    0.09
    ("'"
    0.09
    trä
    0.09
    ä½ľä¸ºä¸ĢåIJį
    0.09
    ties
    0.09
    yahoo
    0.09
    ãģªãģĮãĤī
    0.09
    Activations Density 0.006%

    No Known Activations