© 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. 23125
    Prev
    Next
    INDEX
    Explanations

    I/we can

    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
    çIJĨ解åĴĮ
    -0.15
    ç»ıéªĮåĴĮ
    -0.14
    建设åĴĮ
    -0.12
    æŶéĹ´åĴĮ
    -0.12
    æĸĩåĮĸåĴĮ
    -0.12
     however
    -0.11
    è´¨éĩıåĴĮ
    -0.11
    æľįåĬ¡èĥ½åĬĽ
    -0.10
    æĢĿãģĦ
    -0.10
    ä¼ģä¸ļåĴĮ
    -0.10
    POSITIVE LOGITS
    /or
    0.20
    rogen
    0.13
    rew
    0.12
    rog
    0.11
    çĶ±æѤ
    0.11
    ìĭ¶
    0.10
    /OR
    0.10
     consequ
    0.10
    erson
    0.09
     subsequently
    0.09
    Activations Density 0.104%

    No Known Activations