© 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. 11698
    Prev
    Next
    INDEX
    Explanations

    // +build directives

    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
    "
    -0.18
    ³
    -0.17
    &quot
    -0.16
     part
    -0.15
    bery
    -0.15
    places
    -0.15
    -catching
    -0.15
    place
    -0.15
     guts
    -0.15
    prints
    -0.14
    POSITIVE LOGITS
    /-
    0.22
    ï¸ı
    0.22
    çħ¦
    0.21
    /OR
    0.21
    erior
    0.18
    itional
    0.18
    iton
    0.18
    itive
    0.18
    gether
    0.18
    ITIVE
    0.18
    Activations Density 0.134%

    No Known Activations