© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53220
    Prev
    Next
    INDEX
    Explanations

    into a word

    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
    _clip
    -0.08
    ãģ¡ãĤī
    -0.08
    less
    -0.08
    ham
    -0.08
     HAR
    -0.08
    ä¼ļéķ¿
    -0.08
    ets
    -0.08
     clip
    -0.08
    omore
    -0.08
    éĴī
    -0.07
    POSITIVE LOGITS
    æ®Ĩ
    0.10
    æݪ
    0.09
    çĦ¦çĤ¹
    0.09
    æļ®
    0.09
    çĶ¨æĪ·æıIJä¾Ľ
    0.08
    è¿Ļç§įäºĭæĥħ
    0.08
    ãģ£ãģ±
    0.08
    è¿Ļç±»
    0.08
    åħ¨åĽ½äººå¤§
    0.08
    æݩ饰
    0.08
    Activations Density 0.011%

    No Known Activations