© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16929
    Prev
    Next
    INDEX
    Explanations

    OpenFOAM solver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    _Parms
    -0.24
    GenerationStrategy
    -0.22
    estival
    -0.22
    éĵ½
    -0.21
    ledon
    -0.21
    ouro
    -0.21
    裣
    -0.20
    owa
    -0.20
    fitness
    -0.20
    IDEOS
    -0.20
    POSITIVE LOGITS
     solver
    0.26
    解åĨ³éĹ®é¢ĺ
    0.25
     fluid
    0.24
     solving
    0.24
     discret
    0.24
    éĹ®é¢ĺ
    0.24
     numerical
    0.24
    åīĸ
    0.23
    _solve
    0.23
     fluids
    0.22
    Activations Density 0.266%

    No Known Activations