© 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. 3177
    Prev
    Next
    INDEX
    Explanations

    post office, wood frame, National Register

    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
    彪
    -0.10
    æµij
    -0.09
    æııåĨĻ
    -0.09
    åľ¨å¹¿å·ŀ
    -0.09
    rvine
    -0.09
    æ´Ħ
    -0.08
     peri
    -0.08
    éĩİå¤ĸ
    -0.08
    å¯ĨåĪĩ
    -0.08
    æ£ī
    -0.08
    POSITIVE LOGITS
    çªĹ
    0.11
     sweep
    0.10
    马æĭī
    0.10
    обÑĢа
    0.09
    æĪ·
    0.09
    éĢģè¾¾
    0.09
    /apis
    0.09
    è¾Ļ
    0.09
    åħ»çĮª
    0.09
    汽油
    0.09
    Activations Density 0.345%

    No Known Activations