© 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. 32219
    Prev
    Next
    INDEX
    Explanations

    interface elements

    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
    ffer
    -0.09
    COVER
    -0.09
    为广大
    -0.09
    å¾ĹæĦı
    -0.08
    hazi
    -0.08
    æģ¶åĮĸ
    -0.08
    常年
    -0.08
    åıijå±ķä¸Ń
    -0.08
     Barg
    -0.08
    ä¸įå¼Ģ
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģä¼ļ
    0.09
    èĥ¶åĽĬ
    0.08
    arias
    0.08
     bidi
    0.08
    ISR
    0.08
    ivec
    0.08
    çŃĮ
    0.08
    çŃīåĬŁèĥ½
    0.08
    centage
    0.08
    istant
    0.08
    Activations Density 0.127%

    No Known Activations