© 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. 4736
    Prev
    Next
    INDEX
    Explanations

    square root and root operations

    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
    invalidate
    -0.08
    ARB
    -0.08
     sweeping
    -0.08
    询éĹ®
    -0.08
    éĩĩ访
    -0.08
    çĽijçĿ£ç®¡çIJĨ
    -0.08
    orges
    -0.08
    á»ļ
    -0.08
    affen
    -0.08
    bsp
    -0.08
    POSITIVE LOGITS
    æł¹
    0.10
     root
    0.10
    ä¸įåħĭ
    0.10
    _root
    0.10
    _ROOT
    0.10
    Root
    0.09
    getRoot
    0.09
    ç»ıå¼Ģ
    0.09
    .Root
    0.09
    å¾Ĺ天
    0.09
    Activations Density 0.149%

    No Known Activations