© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12327
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    åij»
    -0.19
     floats
    -0.19
    åŁĭ
    -0.18
    .Home
    -0.18
    crement
    -0.18
     commons
    -0.18
    è¿Ķ乡
    -0.18
     cogn
    -0.18
    éĨĴ
    -0.18
    /inc
    -0.18
    POSITIVE LOGITS
    æľ¨åľ°æĿ¿
    0.19
    ä¸įå±ij
    0.19
    å¯Ħ
    0.18
    æIJºå¸¦
    0.18
    orm
    0.18
     bamb
    0.17
    pairs
    0.17
    wo
    0.17
    éĤij
    0.17
    Expose
    0.17
    Activations Density 0.005%

    No Known Activations