© 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. 2218
    Prev
    Next
    INDEX
    Explanations

    Carter or Red Bull

    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
    onta
    -0.09
    äºijéĽĨ
    -0.09
    ATOR
    -0.09
    conti
    -0.08
    éħİ
    -0.08
    compat
    -0.08
     Ñģобой
    -0.08
    .loads
    -0.08
    çªł
    -0.08
    ighting
    -0.08
    POSITIVE LOGITS
    å¼łè´´
    0.09
    åıªéľĢ
    0.08
    ugi
    0.08
    ä¹Łæĺ¯ä¸Ģ个
    0.08
    æĪı
    0.08
    åģļåĪ°äºĨ
    0.08
    åŁºå±Ĥ
    0.08
    æĪ²
    0.08
    zan
    0.08
    å¾Ģå¤ĸ
    0.08
    Activations Density 0.003%

    No Known Activations