© 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. 16449
    Prev
    Next
    INDEX
    Explanations

    local, cloud, or self-hosted deployment

    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
    ÃŃcia
    -0.21
    atee
    -0.20
     Threads
    -0.20
     Cro
    -0.19
    .currentTarget
    -0.19
    ston
    -0.18
     cro
    -0.18
    磧
    -0.18
    arResult
    -0.18
    ORIGINAL
    -0.18
    POSITIVE LOGITS
    æľ¬åľ°
    0.24
    èĩªä¸»
    0.21
    èĥļ
    0.21
    èħ´
    0.21
    äºij
    0.20
    ç¡®
    0.20
     private
    0.19
    /cloud
    0.19
    çĭ¬ç«ĭ
    0.19
    å¢ĥåĨħ
    0.19
    Activations Density 0.059%

    No Known Activations