© 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. 4594
    Prev
    Next
    INDEX
    Explanations

    configuration

    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
    诸å¦Ĥ
    -0.11
    çĪ¸å¦Ī
    -0.10
    éĤ£ä¹Īç®Ģåįķ
    -0.09
     (↵
    -0.09
    Âł
    -0.09
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.08
    åī¡
    -0.08
    éĤ£ç§į
    -0.08
    ä¸įä¹ħ
    -0.08
    ä¸Ģ个个
    -0.08
    POSITIVE LOGITS
    åģ·
    0.09
    'icon
    0.09
     Uncomment
    0.08
    .PI
    0.08
    ä¸ĩä¸Ģ
    0.08
    ÖĦ
    0.08
    WARE
    0.08
    -www
    0.08
     Kimber
    0.08
    nees
    0.08
    Activations Density 0.957%

    No Known Activations