© 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. 27326
    Prev
    Next
    INDEX
    Explanations

    create or invent solutions

    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
    ÑĢаз
    -0.10
    uary
    -0.08
    اÙĪ
    -0.08
    OrCreate
    -0.08
    ãģ¤ãģ¤
    -0.08
    äºĭåħĪ
    -0.08
    uzzi
    -0.08
     Forever
    -0.07
    .Unsupported
    -0.07
    毫ä¸įçĬ¹è±«
    -0.07
    POSITIVE LOGITS
    ftware
    0.11
     Ñģебе
    0.10
    ively
    0.10
    otlin
    0.10
    ible
    0.10
    äºĨä¸Ģåľº
    0.09
    axter
    0.09
    åĩºè®©
    0.09
    让æ¶Īè´¹èĢħ
    0.09
    ermen
    0.09
    Activations Density 0.009%

    No Known Activations