© 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. 22439
    Prev
    Next
    INDEX
    Explanations

    in and around

    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
    aison
    -0.10
    à¹ĭ
    -0.09
    Æ°Æ¡
    -0.09
    asco
    -0.09
    áºŃp
    -0.09
    etti
    -0.08
    ãģªãģı
    -0.08
     chù
    -0.08
    intree
    -0.08
    è±ī
    -0.08
    POSITIVE LOGITS
    éĢĶ
    0.09
    è®°è½½
    0.09
    èĦı
    0.09
    游åĩ»
    0.08
    两æĿ¡
    0.08
    建档ç«ĭåį¡
    0.08
    åıįæŃ£
    0.08
    çļĦçݰ象
    0.08
     sur
    0.08
    峪
    0.08
    Activations Density 0.027%

    No Known Activations