© 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. 6516
    Prev
    Next
    INDEX
    Explanations

    radiation therapy

    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
    åı£æ°Ķ
    -0.10
    åīįåı°
    -0.10
    æĩĴ
    -0.09
     полÑĥ
    -0.09
    æ´»è·ĥ
    -0.09
    à¸Ľà¸£à¸°à¸Īำ
    -0.08
     Glyph
    -0.08
    atego
    -0.08
    lector
    -0.08
    ibles
    -0.08
    POSITIVE LOGITS
    abra
    0.09
    iele
    0.09
     bunker
    0.08
     Beckham
    0.08
     Teddy
    0.08
    tod
    0.08
    ç½ijç«Ļåľ°åĽ¾
    0.08
    ponsive
    0.08
    رس
    0.08
     dÄ±ÅŁÄ±
    0.08
    Activations Density 0.083%

    No Known Activations