© 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. 18613
    Prev
    Next
    INDEX
    Explanations

    search results or formatting

    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
    æķĻæ¡Ī
    -0.10
    izr
    -0.08
    ughty
    -0.08
    èĢĮåıĪ
    -0.08
    ug
    -0.08
    alted
    -0.08
     bleed
    -0.08
    并ä¸Ķ
    -0.08
    Č
    -0.08
    formance
    -0.08
    POSITIVE LOGITS
     ÑĤоже
    0.10
    æļĿ
    0.10
    ç»ĪçĶŁ
    0.08
    åIJ¬è¯´è¿ĩ
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    æĪij没
    0.08
    ç´§æİ¥çĿĢ
    0.08
     ÑģобÑģÑĤвенно
    0.08
    igg
    0.08
    æĺ¯åĽłä¸º
    0.08
    Activations Density 0.864%

    No Known Activations