© 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. 54359
    Prev
    Next
    INDEX
    Explanations

    nuclear option

    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
    éĻ¶
    -0.10
    åħ¥æĪ·
    -0.10
    arrant
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    ä¸Ŀ
    -0.09
    å©¿
    -0.08
    æĿŀ
    -0.08
    .VAL
    -0.08
    ictured
    -0.08
     LIABILITY
    -0.08
    POSITIVE LOGITS
    审议
    0.13
     recess
    0.12
    å±¥èģĮ
    0.10
    对åĨ³
    0.10
    é¢Ħç®Ĺ
    0.10
    人大常å§Ķ
    0.09
    åħ¨åĽ½äººå¤§
    0.09
    人大
    0.09
     House
    0.09
     historical
    0.09
    Activations Density 0.200%

    No Known Activations