© 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. 1280
    Prev
    Next
    INDEX
    Explanations

    fluid dynamics, circulation, velocities

    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
    åºŁ
    -0.10
     ÑĢа
    -0.09
    emies
    -0.09
    å±±åĿ¡
    -0.09
    èµĦ产è¯Ħä¼°
    -0.09
    acci
    -0.09
    奸
    -0.08
    éĹ¹
    -0.08
    aravel
    -0.08
    ousse
    -0.08
    POSITIVE LOGITS
    erna
    0.10
     circulation
    0.09
    ROTO
    0.09
    è¿IJ转
    0.09
    颤æĬĸ
    0.09
    èijĽ
    0.08
     contingent
    0.08
    nofollow
    0.08
     dub
    0.08
    éħ±æ²¹
    0.08
    Activations Density 0.046%

    No Known Activations