© 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. 62782
    Prev
    Next
    INDEX
    Explanations

    undergraduate teaching and students

    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
    åĽłåľ°
    -0.11
    .await
    -0.10
    äºĶæĺŁ
    -0.10
    æĺ¥èĬĤæľŁéĹ´
    -0.10
    åĢ¼å¾Ĺä¸Ģ
    -0.10
    çĿ½
    -0.10
    Ùħد
    -0.10
     оÑĤд
    -0.10
    oha
    -0.09
     SENSOR
    -0.09
    POSITIVE LOGITS
    æ²¥
    0.09
     covered
    0.08
     Bank
    0.08
     bank
    0.08
     falling
    0.08
     Wh
    0.08
    fall
    0.08
    绣é¢Ĩ
    0.08
    Wh
    0.07
    اس
    0.07
    Activations Density 0.070%

    No Known Activations