© 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. 12875
    Prev
    Next
    INDEX
    Explanations

    wired connections and technologies

    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
    veled
    -0.20
    æĦı大
    -0.19
    æĪij以为
    -0.18
    æŃ©
    -0.17
    æĻĸ
    -0.17
    å¤©çľŁ
    -0.17
    _blocking
    -0.17
    liness
    -0.17
    lé
    -0.16
    IntPtr
    -0.16
    POSITIVE LOGITS
    ëIJľ
    0.19
    ä¸įéĢļ
    0.18
    å¼ĢéĢļ
    0.18
    ../../../
    0.18
     ráp
    0.16
    -complete
    0.16
    sys
    0.16
    -horizontal
    0.15
    vice
    0.15
    สวà¸Ļ
    0.15
    Activations Density 0.010%

    No Known Activations