© 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. 1597
    Prev
    Next
    INDEX
    Explanations

    with a quantity or time remaining

    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
    à¹Ģสมà¸Ń
    -0.09
     penny
    -0.08
    è¦Ĩ
    -0.08
    aro
    -0.08
    rollers
    -0.08
    fal
    -0.08
     пеÑĩ
    -0.08
    çįIJ
    -0.08
    _visibility
    -0.08
     ephem
    -0.08
    POSITIVE LOGITS
    åī©
    0.12
    åī©ä½Ļ
    0.12
    å¼¼
    0.10
    æľŁéĻIJ
    0.10
    宦
    0.10
    remaining
    0.09
     Nev
    0.09
    avern
    0.09
    æĹ¥æ¸IJ
    0.09
    åī©ä¸ĭçļĦ
    0.09
    Activations Density 0.042%

    No Known Activations