© 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. 35412
    Prev
    Next
    INDEX
    Explanations

    fastest growing, faster access

    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
    еле
    -0.09
    ä¿Ĥ
    -0.09
    æ¦ľ
    -0.09
    è´Łè´£ä»»
    -0.09
    rish
    -0.09
    amble
    -0.09
    é§IJ
    -0.09
    è¾Ķ
    -0.08
    lia
    -0.08
    åIJ¬çĿĢ
    -0.08
    POSITIVE LOGITS
    idious
    0.16
    -paced
    0.15
     paced
    0.13
     chóng
    0.13
    stm
    0.10
    æµģéĢĿ
    0.10
    åıĺè¿ģ
    0.10
    -growing
    0.09
    赶æĿ¥
    0.09
     pace
    0.09
    Activations Density 0.095%

    No Known Activations