© 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. 63243
    Prev
    Next
    INDEX
    Explanations

    months or dates

    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
    èĵĭ
    -0.09
    _CHIP
    -0.09
    çĽĸ
    -0.08
    ç©°
    -0.08
    Ħ件
    -0.08
    é©¿
    -0.08
    æĸ°å»º
    -0.08
     dirty
    -0.08
    äºĨå¤ļå°ij
    -0.08
    åĬłçĽĸ
    -0.08
    POSITIVE LOGITS
    æĭ¾
    0.09
    èµ·æŃ¥
    0.09
    unsubscribe
    0.08
    订éĺħ
    0.08
    .AC
    0.08
    ä¸įæĿ¥
    0.08
    STONE
    0.08
    cus
    0.08
    رÙĪس
    0.08
    ords
    0.08
    Activations Density 0.105%

    No Known Activations