© 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. 57476
    Prev
    Next
    INDEX
    Explanations

    cinnamon

    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
    ILITY
    -0.09
    å¼Ħå¾Ĺ
    -0.09
    èµ°åľ¨
    -0.09
    éĿĽ
    -0.09
    ouncill
    -0.09
    ibble
    -0.09
    PY
    -0.08
    inion
    -0.08
    ility
    -0.08
    çĥ¹
    -0.08
    POSITIVE LOGITS
     Dul
    0.09
    URED
    0.09
    æĽ¦
    0.08
    acho
    0.08
    éĽĨåĽ¢èĤ¡ä»½
    0.08
    èĿł
    0.08
    åĽĽæĸ¹
    0.08
    æĻ°
    0.08
    åĮĿ
    0.08
    æ¦Ķ
    0.08
    Activations Density 0.004%

    No Known Activations