© 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. 17799
    Prev
    Next
    INDEX
    Explanations

    dual licensed

    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
    å¤ļåħĥåĮĸ
    -0.09
    æŀ°
    -0.08
    éªĬ
    -0.08
    ä»»ä½ķå½¢å¼ı
    -0.08
    èŃĺ
    -0.08
    åħ¨åĽ½äººæ°ij
    -0.08
    инÑĦ
    -0.08
    rück
    -0.08
     ALOG
    -0.08
    ahl
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.15
    double
    0.15
     double
    0.13
    -double
    0.13
    ,double
    0.12
    (double
    0.12
    /single
    0.12
    DOUBLE
    0.11
    åıĮéĩį
    0.11
     Double
    0.11
    Activations Density 0.230%

    No Known Activations