© 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. 55268
    Prev
    Next
    INDEX
    Explanations

    to see if

    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
    cy
    -0.10
    çķļ
    -0.09
    姥
    -0.09
    å¾Īåı¯èĥ½
    -0.09
    <?,
    -0.09
    æĶĺ
    -0.09
    æĴ¸
    -0.09
    (non
    -0.09
    æ¦Ķ
    -0.09
    .cy
    -0.09
    POSITIVE LOGITS
    æľīå¤ļå°ij
    0.10
    æĪijèĥ½
    0.09
    çĦĺ
    0.08
    imonials
    0.08
    acular
    0.08
    ught
    0.08
    åı¯ä»¥èİ·å¾Ĺ
    0.08
    reate
    0.08
     overall
    0.08
    å¥ī
    0.08
    Activations Density 0.018%

    No Known Activations