© 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. 22017
    Prev
    Next
    INDEX
    Explanations

    little is known/considered

    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
    å¾ĢæĿ¥
    -0.10
    çī§
    -0.08
     Weber
    -0.08
    roke
    -0.08
    lds
    -0.08
    æĽ
    -0.08
     incon
    -0.08
    _embed
    -0.08
    ixa
    -0.08
    æī¿
    -0.08
    POSITIVE LOGITS
     about
    0.15
    about
    0.14
     عÙĨÙĩا
    0.13
     vá»ģ
    0.12
     ABOUT
    0.12
    _about
    0.12
    åħ³äºİ
    0.12
     знаÑĤÑĮ
    0.11
    æ¦ĤåĨµ
    0.11
     hakkında
    0.11
    Activations Density 0.087%

    No Known Activations