© 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. 23808
    Prev
    Next
    INDEX
    Explanations

    importance

    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
     главное
    -0.09
    moth
    -0.09
    Ign
    -0.09
    æĪª
    -0.08
    éĻ¤æѤ
    -0.08
    lems
    -0.08
    mpp
    -0.08
    aldo
    -0.08
    åĮ£
    -0.08
    isches
    -0.08
    POSITIVE LOGITS
    HostException
    0.10
    åIJ¬åIJ¬
    0.09
     جدا
    0.09
    çļĦæĺ¯
    0.09
    ista
    0.09
     multim
    0.09
    jom
    0.09
    ãģªãģĮãĤī
    0.09
    .aspect
    0.08
    _MARKER
    0.08
    Activations Density 0.033%

    No Known Activations