© 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. 56725
    Prev
    Next
    INDEX
    Explanations

    K words, Kubernetes, Ktor

    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
    ढ
    -0.11
    ราย
    -0.10
    KeyPress
    -0.10
    kick
    -0.10
    ги
    -0.10
    ear
    -0.09
    KeyEvent
    -0.09
    combe
    -0.09
    KeySpec
    -0.09
    _keyword
    -0.09
    POSITIVE LOGITS
    etchup
    0.15
    rypton
    0.15
    appa
    0.13
    nap
    0.13
    aspers
    0.13
     vá»±c
    0.13
    綮
    0.13
    nowledge
    0.13
    cloak
    0.12
    åĦ¡
    0.11
    Activations Density 0.977%

    No Known Activations