© 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. 32640
    Prev
    Next
    INDEX
    Explanations

    file extensions and website domains

    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
    pet
    -0.10
    ault
    -0.09
    ariant
    -0.09
     налиÑĩие
    -0.09
    Vs
    -0.08
    =back
    -0.08
     ÑıзÑĭк
    -0.08
    è¿Ń
    -0.08
    croll
    -0.08
    ä¾Ŀæīĺ
    -0.08
    POSITIVE LOGITS
    çĨı
    0.10
    æĺ¶
    0.10
    ä¸Ģ棵
    0.09
    ละ
    0.09
    èĸ°
    0.09
    饿
    0.08
    åĭĥ
    0.08
    Chron
    0.08
    ä¸Ģç»ı
    0.08
    esser
    0.08
    Activations Density 0.253%

    No Known Activations