© 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. 27738
    Prev
    Next
    INDEX
    Explanations

    ingredients and recipe steps

    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
    mmas
    -0.11
    AREN
    -0.10
    ÑĢай
    -0.10
    çĩł
    -0.10
    æķ·
    -0.10
    odies
    -0.09
    .splitext
    -0.09
    .EditValue
    -0.09
    æ·Ģ
    -0.09
    itol
    -0.09
    POSITIVE LOGITS
     except
    0.09
     ingredients
    0.09
    Except
    0.09
    ä¸Ģèµ·
    0.08
    åı¯ä»¥ä½¿
    0.08
    åľ¨ä¸Ģèµ·
    0.08
    ä¸Ģèµ·åİ»
    0.08
     together
    0.08
    eller
    0.08
    ä¸ĢæľŁ
    0.08
    Activations Density 0.008%

    No Known Activations