© 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. 61633
    Prev
    Next
    INDEX
    Explanations

    content amount

    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
    人æķ°
    -0.10
    подоб
    -0.09
    é¦Ī
    -0.09
    вали
    -0.09
    人åı£
    -0.08
    æĦŁ
    -0.08
    Clr
    -0.08
    å§ĵ
    -0.08
     Globals
    -0.08
    PAIR
    -0.08
    POSITIVE LOGITS
    åIJ«éĩı
    0.19
    åIJ«ãģ¾ãĤĮ
    0.12
     content
    0.12
     ÑģодеÑĢж
    0.12
    åIJ«
    0.11
    åIJ«æľī
    0.11
    æĪIJåĪĨ
    0.11
     contained
    0.11
    æĪIJ份
    0.10
    ä¸įåIJ«
    0.10
    Activations Density 0.177%

    No Known Activations