© 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. 22972
    Prev
    Next
    INDEX
    Explanations

    store or storing data

    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
    sert
    -0.13
    индивид
    -0.09
    æ°´æµģ
    -0.09
    .RequestBody
    -0.09
    ekt
    -0.09
    ÑĩÑĢ
    -0.09
    .forChild
    -0.09
    ewn
    -0.09
    åī²
    -0.09
    lic
    -0.08
    POSITIVE LOGITS
    OrUpdate
    0.16
    ä¸įä½ı
    0.13
     trữ
    0.10
    è´®
    0.10
    äºĨ大éĩıçļĦ
    0.10
    åĤ¨
    0.09
    åĤ¨åŃĺ
    0.09
    é¹°
    0.09
    éĽħ
    0.09
    侥幸
    0.09
    Activations Density 0.137%

    No Known Activations