© 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. 18416
    Prev
    Next
    INDEX
    Explanations

    about

    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
    èĮĤ
    -0.09
    igr
    -0.08
    è¾ŀ
    -0.08
    åĩłå¼ł
    -0.08
    Hell
    -0.08
    lys
    -0.08
    InThe
    -0.08
    俪
    -0.08
    ä»°
    -0.08
     loose
    -0.08
    POSITIVE LOGITS
    åħ³äºİ
    0.22
     about
    0.21
     tentang
    0.19
     vá»ģ
    0.18
    about
    0.17
    éĹľæĸ¼
    0.17
     عÙĨ
    0.16
     sobre
    0.15
     ABOUT
    0.15
     عÙĨÙĩ
    0.15
    Activations Density 0.160%

    No Known Activations