© 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. 11828
    Prev
    Next
    INDEX
    Explanations

    percent, comma, unit

    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
     Rect
    -0.20
    éħ¬
    -0.20
    è±Ĩçĵ£
    -0.19
     Radi
    -0.19
     colspan
    -0.18
     Stroke
    -0.18
    indrome
    -0.18
    chron
    -0.18
     Vict
    -0.17
    justify
    -0.17
    POSITIVE LOGITS
    éĩįä¸Ń
    0.22
    ç»ĩ
    0.21
    itti
    0.20
    çļ±
    0.20
    oseconds
    0.19
    山寨
    0.19
    åģ¥åº·äº§ä¸ļ
    0.19
    åij»
    0.18
    pci
    0.18
     FileAccess
    0.18
    Activations Density 0.044%

    No Known Activations