© 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. 61609
    Prev
    Next
    INDEX
    Explanations

    Navajo Nation

    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
    JNI
    -0.09
    æĸ°è¥¿åħ°
    -0.09
    _rc
    -0.08
    èĢĢ
    -0.08
    bil
    -0.08
    æīĪ
    -0.08
    azon
    -0.08
    åıĺå¼Ĥ
    -0.08
    å½ĵåľ°äºº
    -0.08
    å¼ĵ
    -0.07
    POSITIVE LOGITS
    çĺ¸
    0.10
    æĺ¥æĻļ
    0.09
    好çľĭçļĦ
    0.09
    è¹ij
    0.09
    iences
    0.09
    èĨĺ
    0.09
    èĤº
    0.09
    Tube
    0.09
    PTION
    0.09
    诬
    0.09
    Activations Density 0.018%

    No Known Activations