© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21449
    Prev
    Next
    INDEX
    Explanations

    film release 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
     BASIS
    -0.09
    ç¿ķ
    -0.09
    åĶī
    -0.09
    изм
    -0.09
    ä¸Ģ大
    -0.09
    ëŁŃ
    -0.08
    积æŀģåĵįåºĶ
    -0.08
    allen
    -0.08
    izioni
    -0.08
    åħ¨å±Ģ
    -0.08
    POSITIVE LOGITS
    ä¸ŃåĽ½åĪ¶éĢł
    0.10
    æĸ°ä¸ĸ纪
    0.09
    麻辣
    0.09
    èıľé¸Ł
    0.09
     mer
    0.08
     tat
    0.08
    æŁľåı°
    0.08
    è¿Ļéĥ¨çĶµå½±
    0.08
    çīĮ
    0.08
    æ»ĭåij³
    0.08
    Activations Density 0.356%

    No Known Activations