© 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. 3881
    Prev
    Next
    INDEX
    Explanations

    number of people

    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
     Photon
    -0.09
    éļ¶å±ŀ
    -0.09
    2
    -0.08
    èĩªæĦ¿
    -0.08
    _agents
    -0.08
     Bethesda
    -0.08
    imos
    -0.08
    6
    -0.08
    ä¸Ģåı¥
    -0.08
    7
    -0.08
    POSITIVE LOGITS
    aber
    0.11
    æīĢèĥ½
    0.10
    åı¯æݧ
    0.10
     hiá»ĥn
    0.10
    åı¯ä»¥èİ·å¾Ĺ
    0.10
    èĥ½å¤Łåľ¨
    0.10
    è¿ŀå¿Ļ
    0.09
    æī¿æĭħ责任
    0.09
    åĵ½
    0.09
    osten
    0.09
    Activations Density 0.144%

    No Known Activations