© 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. 27826
    Prev
    Next
    INDEX
    Explanations

    evaluates, resolves, adds, translates

    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
    GLOBALS
    -0.09
    åı°ä¸Ĭ
    -0.09
    è¡£
    -0.08
    äºĨ解
    -0.08
    趱
    -0.08
    lav
    -0.08
    ivel
    -0.08
    ç´§
    -0.08
    ç§Ģ
    -0.08
    ç´§è·Ł
    -0.08
    POSITIVE LOGITS
    èµ·æĿ¥
    0.13
    èµ·ä¾Ĩ
    0.11
    åĩº
    0.10
    æ¯ĶåĪ©
    0.10
    æľįåĬ¡æľºæŀĦ
    0.09
    享åıĹåĪ°
    0.09
    æĸ¹åľĨ
    0.09
     Äijá»±ng
    0.08
    åĩºæĿ¥çļĦ
    0.08
    æľīä¸Ģä½į
    0.08
    Activations Density 0.031%

    No Known Activations