© 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. 23416
    Prev
    Next
    INDEX
    Explanations

    most common/**studied/**important

    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
    .packet
    -0.09
    ç»İ
    -0.09
    å¾®å¦Ļ
    -0.09
    ory
    -0.09
    dap
    -0.08
    éħĿéħ¿
    -0.08
    ä¹Łä¸įèĥ½
    -0.08
    åIJ¯ç¤º
    -0.08
    å»ºåĽ½
    -0.08
    æľīåı¯èĥ½
    -0.08
    POSITIVE LOGITS
    æľĢ常è§ģçļĦ
    0.15
    æľĢ为
    0.14
    常è§ģçļĦ
    0.14
    大å¤ļæķ°äºº
    0.12
    常çĶ¨çļĦ
    0.11
    常è§ģ
    0.11
    æ¯Ķè¾ĥå¤ļ
    0.11
    æĺ¯æľĢ
    0.10
    ä¸Ģ个æĺ¯
    0.10
    è¾ĥ为
    0.10
    Activations Density 0.227%

    No Known Activations