© 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. 58919
    Prev
    Next
    INDEX
    Explanations

    Seth followed by names or surnames

    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
    uet
    -0.10
    inating
    -0.09
    eenth
    -0.09
    NAMESPACE
    -0.09
     Circular
    -0.09
    _JUMP
    -0.08
    coli
    -0.08
    доÑĢ
    -0.08
    çĶļèĩ³
    -0.08
    pane
    -0.08
    POSITIVE LOGITS
    çķĮçļĦ
    0.10
    ules
    0.09
    ä¸Ģåı£
    0.09
    åĬ©çIJĨ
    0.09
    abouts
    0.09
    aceous
    0.08
    ropol
    0.08
    tlement
    0.08
    å´¦
    0.08
    主æĦı
    0.08
    Activations Density 0.007%

    No Known Activations