© 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. 63662
    Prev
    Next
    INDEX
    Explanations

    words ending in able or describing movement

    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
    æīĭå¥Ĺ
    -0.09
    æ´Ĺ澡
    -0.08
    goods
    -0.08
    æ¼Ĩ
    -0.08
    çIJ¢
    -0.08
    intern
    -0.07
    çĤ¹å¤ļ
    -0.07
    WAR
    -0.07
    æĪĺåĽ½
    -0.07
     gor
    -0.07
    POSITIVE LOGITS
    åĩºæĿ¥äºĨ
    0.10
    æĭĶ
    0.10
    /rem
    0.10
    ãģ«åĩº
    0.10
    åĩºåİ»
    0.10
     retract
    0.09
    åŁĶ
    0.09
    伸åĩº
    0.09
    æºľ
    0.09
    缩çŁŃ
    0.09
    Activations Density 0.179%

    No Known Activations