© 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. 61518
    Prev
    Next
    INDEX
    Explanations

    right here

    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
    è¿Ļ个èģĮä¸ļ
    -0.09
    饿
    -0.09
    asha
    -0.08
    åĻį
    -0.08
    graphics
    -0.08
    形容
    -0.08
    acker
    -0.08
    åİħ
    -0.08
    imers
    -0.08
    æĢģåĬ¿
    -0.08
    POSITIVE LOGITS
    è¿ľæĸ¹
    0.09
    家乡
    0.09
    乡
    0.09
    åĮ¡
    0.09
    款
    0.09
    åı¤èĢģ
    0.08
     presumption
    0.08
    sav
    0.08
    outside
    0.08
    è¾į
    0.08
    Activations Density 0.043%

    No Known Activations