© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7016
    Prev
    Next
    INDEX
    Explanations

    Android smartphone manufacturers

    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
    esModule
    -0.11
    åľ¨æ·±åľ³
    -0.10
    intros
    -0.10
    escription
    -0.10
    åĿIJä¸ĭ
    -0.10
    åį°ç«ł
    -0.10
    åľ¨åIJĮä¸Ģ
    -0.09
    ecimal
    -0.09
    iscrim
    -0.09
    emap
    -0.09
    POSITIVE LOGITS
    åı¦è¡Į
    0.11
    cone
    0.09
     app
    0.09
    åı¦
    0.09
    cores
    0.08
    åı¦æľī
    0.08
     APK
    0.08
    asar
    0.08
    ky
    0.07
    大æłij
    0.07
    Activations Density 0.087%

    No Known Activations