© 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. 34491
    Prev
    Next
    INDEX
    Explanations

    past events and history

    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
    严èĤĥ
    -0.10
    éĺı
    -0.09
    访
    -0.09
    rench
    -0.09
    åıijçİ°äºĨ
    -0.09
    æĬķ稿
    -0.08
    饱
    -0.08
    åŃ°
    -0.08
    æĢħ
    -0.08
    å±¥èģĮ
    -0.08
    POSITIVE LOGITS
    åİĨåı²ä¸Ĭ
    0.16
     precedent
    0.13
    åİĨåı²
    0.13
    ç»ıéªĮ
    0.12
    以å¾Ģ
    0.12
     pattern
    0.12
     HISTORY
    0.11
     histórico
    0.11
    ãĥijãĤ¿ãĥ¼ãĥ³
    0.11
     history
    0.11
    Activations Density 0.067%

    No Known Activations