© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7660
    Prev
    Next
    INDEX
    Explanations

    time out or timeout

    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
    ä¿İ
    -0.10
    é¦Ĵ头
    -0.09
    çłĴ
    -0.09
    鹧
    -0.08
    hind
    -0.08
    çĥĽ
    -0.08
    horse
    -0.08
    åĿļæĮģ
    -0.08
    çĭ°
    -0.08
    åĨ²åĩ»
    -0.08
    POSITIVE LOGITS
    kits
    0.10
    imized
    0.09
    epad
    0.09
    _sdk
    0.08
    INET
    0.08
     Trib
    0.08
    comma
    0.08
     Calories
    0.08
    ortal
    0.08
    _EQUALS
    0.08
    Activations Density 0.003%

    No Known Activations