© 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. 50286
    Prev
    Next
    INDEX
    Explanations

    default, standard, primary, majority

    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
    è·³åĩº
    -0.10
    äºŃ
    -0.09
    ç¦ģåĮº
    -0.09
    æ¦Ĥ
    -0.09
    å¥łåŁº
    -0.09
    æľĢæĹ©
    -0.08
    å¼Ģåĩº
    -0.08
    积æ·Ģ
    -0.08
     trail
    -0.08
    没åħ³ç³»
    -0.08
    POSITIVE LOGITS
    主æµģ
    0.13
    大éĥ¨åĪĨ
    0.12
    常æĢģ
    0.12
    é»ĺ认
    0.12
     majority
    0.12
    /default
    0.11
     default
    0.11
    ç»Ŀ大å¤ļæķ°
    0.11
     DEFAULT
    0.11
    大å¤ļæķ°
    0.11
    Activations Density 0.137%

    No Known Activations