© 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. 26604
    Prev
    Next
    INDEX
    Explanations

    dedication and determination

    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
    éģij
    -0.10
    æĺİæĹ¥
    -0.09
    anka
    -0.08
    å¼¼
    -0.08
    aring
    -0.08
    æĺİ代
    -0.08
    _NC
    -0.08
    IENT
    -0.08
    èĪ«
    -0.08
    建ç«ĭåģ¥åħ¨
    -0.08
    POSITIVE LOGITS
     öd
    0.09
    åĬ¬
    0.09
    ä¸Ģ次次
    0.09
    è·Ŀ
    0.09
    éĬ®
    0.09
     игÑĢÑĭ
    0.08
     ÑĢабоÑĤÑĭ
    0.08
    产ä¸ļéĽĨ群
    0.08
    Stencil
    0.08
    ложений
    0.08
    Activations Density 0.010%

    No Known Activations