© 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. 20176
    Prev
    Next
    INDEX
    Explanations

    management operations and systems

    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
    管å§Ķä¼ļ
    -0.12
    管çIJĨå±Ģ
    -0.10
    常å§Ķ
    -0.10
    管çIJĨæ°´å¹³
    -0.10
    tings
    -0.10
    ä¸įçŁ¥ä¸įè§ī
    -0.09
    _mgmt
    -0.09
    èŁł
    -0.09
    anja
    -0.09
    ovi
    -0.09
    POSITIVE LOGITS
    çĿ¬
    0.14
    uel
    0.09
    é«®
    0.08
    ODE
    0.08
    ä¹ĭéģĵ
    0.08
    offs
    0.08
    è¿Ļ对
    0.08
    uten
    0.08
    ¨
    0.08
    mel
    0.08
    Activations Density 0.046%

    No Known Activations