© 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. 31936
    Prev
    Next
    INDEX
    Explanations

    Mac OS X

    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
    tid
    -0.09
    åħĪçĶŁ
    -0.08
    èijŃ
    -0.08
    ç»ıçIJĨ
    -0.08
    å½ĵåľ°æĶ¿åºľ
    -0.08
    罩
    -0.08
    æĬµæĬ¼
    -0.08
    è°ĭ
    -0.07
    è¡Įèµ°
    -0.07
    tring
    -0.07
    POSITIVE LOGITS
    acre
    0.11
    es
    0.11
    姹
    0.10
    âĸ¾
    0.09
    ·æĸ°
    0.09
    ä¸ŃæľĢ
    0.09
    ÙĨج
    0.09
    aldi
    0.09
    anson
    0.09
    ä¸ĩ象
    0.09
    Activations Density 0.015%

    No Known Activations