© 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. 17132
    Prev
    Next
    INDEX
    Explanations

    include language constructs

    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
    ASH
    -0.09
    读书
    -0.09
    ró
    -0.09
    omm
    -0.08
    pressive
    -0.08
    æĪª
    -0.08
     scrub
    -0.08
    _Impl
    -0.08
    ä¸İåħ¶
    -0.08
    æľªå¿ħ
    -0.08
    POSITIVE LOGITS
    ooter
    0.10
    äºĶè¡Į
    0.09
    ä¸Ģçīĩ
    0.09
    åĽºå®ļçļĦ
    0.09
    /footer
    0.09
    èī®
    0.09
     Grades
    0.09
    .include
    0.09
    è¿ĽæĿ¥
    0.09
    GLOBALS
    0.09
    Activations Density 0.507%

    No Known Activations