© 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. 4475
    Prev
    Next
    INDEX
    Explanations

    directions and locations

    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
    ä¹İ
    -0.09
    ansk
    -0.09
    å®ıè§Ĥç»ıæµİ
    -0.08
    羣æĥħ
    -0.08
    è¿Ļ两天
    -0.08
    çݰ身
    -0.08
    .Est
    -0.08
    åıĶåıĶ
    -0.08
    奴
    -0.08
    å®ı
    -0.08
    POSITIVE LOGITS
    åİ»çľĭ
    0.11
    ãģ¸
    0.11
     ÑģовеÑĢÑĪ
    0.11
     toward
    0.10
    å·¥ä¸ļåĮĸ
    0.10
    éĻĭ
    0.10
     into
    0.10
    é³ı
    0.10
     towards
    0.10
    ends
    0.09
    Activations Density 0.171%

    No Known Activations