© 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. 62820
    Prev
    Next
    INDEX
    Explanations

    source code and files

    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
    åĨįåĪ°
    -0.09
    å¤ĩ
    -0.09
    icana
    -0.08
    oda
    -0.08
    æĬĹè®®
    -0.08
    atsu
    -0.08
    èģĸ
    -0.08
    _ASSUME
    -0.08
     tph
    -0.08
    elts
    -0.08
    POSITIVE LOGITS
    碼
    0.12
    æ¥Ĥ
    0.09
     innings
    0.09
    à§İ
    0.08
    å½¢å¼ı
    0.08
    çłģ
    0.08
    馥
    0.08
    forge
    0.08
    Forge
    0.08
    ty
    0.08
    Activations Density 0.171%

    No Known Activations