© 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. 31090
    Prev
    Next
    INDEX
    Explanations

    architects and design awards

    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
    ARS
    -0.10
     Clem
    -0.08
    manual
    -0.08
    _manual
    -0.08
    DEV
    -0.08
    -hook
    -0.08
    å¨
    -0.08
    esen
    -0.08
    Ñģло
    -0.07
     pam
    -0.07
    POSITIVE LOGITS
    设计
    0.15
    è¨Ńè¨Ī
    0.14
    设计å¸Ī
    0.14
    设计æĸ¹æ¡Ī
    0.14
    çļĦ设计
    0.13
    design
    0.13
     design
    0.12
    _design
    0.12
     designs
    0.12
    ãĥĩãĤ¶ãĤ¤ãĥ³
    0.12
    Activations Density 0.169%

    No Known Activations