© 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. 20275
    Prev
    Next
    INDEX
    Explanations

    Xbox One

    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
    allon
    -0.10
    åĪĨåħ¬åı¸
    -0.10
    æ·ļ
    -0.09
    ç¶ĵéģİ
    -0.09
    ilos
    -0.09
    iles
    -0.09
     Myers
    -0.09
    ä¸įç»ı
    -0.09
    尽头
    -0.09
    ALLED
    -0.09
    POSITIVE LOGITS
    ä¸ĢæŦ
    0.10
    çļĦçłĶåıij
    0.09
    lect
    0.08
    ÑĢоÑĪ
    0.08
    çłĶåıij
    0.08
    วา
    0.08
     Yok
    0.07
    ä»ĭ
    0.07
    ãģĮãĤī
    0.07
     Nik
    0.07
    Activations Density 0.007%

    No Known Activations