© 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. 2603
    Prev
    Next
    INDEX
    Explanations

    join the conversation

    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
    åIJ»
    -0.10
    殡
    -0.09
    æķ¬è¯·
    -0.09
    çŁ£
    -0.09
    æ§
    -0.09
    aldi
    -0.09
    å¼ĤæĢ§
    -0.09
    容
    -0.09
    _RM
    -0.09
    çŀħ
    -0.09
    POSITIVE LOGITS
    elda
    0.10
    iaux
    0.09
    anan
    0.09
    åı¹æģ¯
    0.09
    omap
    0.09
    缺åı£
    0.09
    æ£ķ
    0.09
    讨论
    0.09
     بذÙĦÙĥ
    0.08
    æŃ»è§Ĵ
    0.08
    Activations Density 0.017%

    No Known Activations