© 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. 61174
    Prev
    Next
    INDEX
    Explanations

    QR codes and barcodes

    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
    éĹŃ
    -0.10
    WSC
    -0.09
    åĿļæĮģ
    -0.09
    å¸Ŀçİĭ
    -0.08
    ẫ
    -0.08
    éĸī
    -0.08
    fare
    -0.08
     carr
    -0.08
    èĦı
    -0.08
    åıijæī¬
    -0.08
    POSITIVE LOGITS
    äºĮç»´çłģ
    0.17
     QR
    0.15
    æī«çłģ
    0.13
     qr
    0.12
    åIJįçīĩ
    0.11
    QR
    0.11
     linking
    0.10
    æī«ä¸Ģæī«
    0.10
    _GUID
    0.09
    qr
    0.09
    Activations Density 0.046%

    No Known Activations