© 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. 56313
    Prev
    Next
    INDEX
    Explanations

    wont do

    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
     Liber
    -0.09
    zones
    -0.09
    _zone
    -0.09
     никак
    -0.08
    .Abstractions
    -0.08
    acks
    -0.08
    å®ĮäºĨ
    -0.08
     Graves
    -0.08
    ä¸į解
    -0.08
    ocs
    -0.08
    POSITIVE LOGITS
    åıªå¥½
    0.11
    éĤ£æł·
    0.11
    çİ°å®ŀä¸Ń
    0.10
    åıªèĥ½è¯´
    0.10
    éĤ£æł·çļĦ
    0.10
    çݺ
    0.10
    éĢīæĭ©äºĨ
    0.10
    åıªèĥ½
    0.10
    æĺ¯æĪij
    0.09
    æĭĸ
    0.09
    Activations Density 0.110%

    No Known Activations