© 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. 13018
    Prev
    Next
    INDEX
    Explanations

    keyword

    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
    è¶Ł
    -0.20
    ctic
    -0.19
    LLU
    -0.18
    anos
    -0.18
    ä¸Ģè¶Ł
    -0.17
    ees
    -0.17
    oming
    -0.17
    åŃĹåı·
    -0.16
    eenth
    -0.16
    born
    -0.16
    POSITIVE LOGITS
    atch
    0.19
    age
    0.19
    sex
    0.19
     phrase
    0.18
    æĻ¯å¾·
    0.17
    (s
    0.17
    ages
    0.17
     vá»±c
    0.17
    æĽ©
    0.17
    ÑĢ
    0.16
    Activations Density 0.012%

    No Known Activations