© 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. 48299
    Prev
    Next
    INDEX
    Explanations

    `able`, `incapable`, `abilities`, `capable`

    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
    ãģ¿ãģ¦
    -0.09
    è¦ģä¸įè¦ģ
    -0.09
    é«ĺä½İ
    -0.09
    è¦ģèĢĥèĻij
    -0.09
    æ³ķå®ļ
    -0.09
    åĴ¬
    -0.09
    åĪ©çĽĬ
    -0.08
    èµĮ
    -0.08
    è§Ī
    -0.08
     Bod
    -0.08
    POSITIVE LOGITS
    驾é©Ń
    0.16
    èĥ½åĬĽ
    0.14
    çļĦèĥ½åĬĽ
    0.14
    èĥ½åĬĽå¼º
    0.13
    èĥľä»»
    0.13
     capable
    0.12
    æľ¬äºĭ
    0.12
    æľīèĥ½åĬĽ
    0.12
     abilities
    0.11
    æĵħéķ¿
    0.11
    Activations Density 0.148%

    No Known Activations