© 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. 62742
    Prev
    Next
    INDEX
    Explanations

    make sure you

    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
    å®Į
    -0.09
    anke
    -0.09
    羡
    -0.09
    ä¸į容æĺĵ
    -0.09
     Shea
    -0.09
    ste
    -0.08
    ozilla
    -0.08
    .goto
    -0.08
    allee
    -0.08
    åıĺæĽ´
    -0.08
    POSITIVE LOGITS
    uring
    0.11
    æİĸ
    0.10
    éĩ
    0.09
    åģļåĪ°
    0.09
    æĺ¯çĶ±
    0.09
    ricks
    0.08
    èĩªå·±çļĦ
    0.08
    URING
    0.08
    æĹłæīĢè°ĵ
    0.08
    å¥¹åľ¨
    0.08
    Activations Density 0.012%

    No Known Activations