© 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. 17965
    Prev
    Next
    INDEX
    Explanations

    Reviews, albums, or categories

    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
    åIJĦèĩª
    -0.12
    åIJĦèĩªçļĦ
    -0.12
    queda
    -0.09
     ÑģооÑĤвеÑĤ
    -0.08
    å¹²äºĭåĪĽä¸ļ
    -0.08
    obel
    -0.08
    æī£éĻ¤
    -0.08
    sWith
    -0.08
    strap
    -0.08
    æĻ¨æĬ¥
    -0.08
    POSITIVE LOGITS
    ä¸ĢçĤ¹åĦ¿
    0.09
    çŀĭ
    0.09
    ä¸ĢçĤ¹
    0.09
    mia
    0.08
    æ§ĺ
    0.08
    æīĵçł´äºĨ
    0.08
    å¹Ķ
    0.08
    주ëĬĶ
    0.08
    IVAL
    0.08
    ä¸Ģåı£æ°Ķ
    0.08
    Activations Density 0.278%

    No Known Activations