© 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. 7305
    Prev
    Next
    INDEX
    Explanations

    just or simply

    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
    Õ¼
    -0.09
    æ·º
    -0.09
    æµħ
    -0.09
    rai
    -0.08
    /Images
    -0.08
    ä»ģ
    -0.08
    _startup
    -0.08
    opo
    -0.08
    ORA
    -0.08
    bih
    -0.08
    POSITIVE LOGITS
    åįķ纯çļĦ
    0.13
    åįķ纯
    0.13
    纯粹
    0.12
     outright
    0.10
     simply
    0.10
    ç´Ķ
    0.10
    纯
    0.09
    åĻ¨åħ·
    0.09
    åIJĦè¡Į
    0.09
     plain
    0.09
    Activations Density 0.039%

    No Known Activations