© 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. 50854
    Prev
    Next
    INDEX
    Explanations

    "AS IS" without warranties

    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
    ä¸įåĩºæĿ¥
    -0.10
    dorf
    -0.09
    åŀĤ
    -0.09
    èĥľåĪ©
    -0.08
    .tight
    -0.08
    è´»
    -0.08
    èĢĹ
    -0.08
    angel
    -0.08
    .Trace
    -0.08
    æĹ©çĤ¹
    -0.08
    POSITIVE LOGITS
    æĿ¥åĽŀ
    0.10
    åģ¶
    0.10
     Murdoch
    0.09
    бо
    0.09
    Ñİ
    0.09
    çĸĻ
    0.09
    ä¸ĩæĪ·
    0.09
    ä¸Ģä¼ļ
    0.09
    åĹĵåŃIJ
    0.09
    åģ¶çĦ¶
    0.09
    Activations Density 0.373%

    No Known Activations