© 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. 30807
    Prev
    Next
    INDEX
    Explanations

    Spielberg, Monterey, Guerrero

    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
     Flat
    -0.09
    iox
    -0.09
    ilda
    -0.09
    Flat
    -0.09
     lud
    -0.09
    uet
    -0.08
    busters
    -0.08
     elbow
    -0.08
    sj
    -0.08
    less
    -0.08
    POSITIVE LOGITS
    olle
    0.10
    åħ³éĶ®æĺ¯
    0.10
    骼
    0.09
    宾é¦Ĩ
    0.09
    æ¯Ľå·¾
    0.09
    æµ·æ¹¾
    0.09
    åĿıäºĨ
    0.09
    裹
    0.09
     Peninsula
    0.09
    oct
    0.09
    Activations Density 0.001%

    No Known Activations