© 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. 14152
    Prev
    Next
    INDEX
    Explanations

    titles and names

    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
    çĪ±ç¾İ
    -0.23
    åĿ¡
    -0.23
    éĴµ
    -0.22
    vens
    -0.21
     оÑĦоÑĢмлен
    -0.20
    å¾Īæ·±
    -0.19
    iming
    -0.18
    winner
    -0.18
    å¾Īå¿«
    -0.18
    ä¸ĢåŃĹ
    -0.18
    POSITIVE LOGITS
     tail
    0.23
    åĢ¦
    0.23
    å°¾
    0.20
    åºĵåŃĺ
    0.19
    çݯç»ķ
    0.19
    åĮĿ
    0.19
    æ³³
    0.19
    羣æĥħ
    0.19
    interop
    0.19
    æ¶İ
    0.19
    Activations Density 0.002%

    No Known Activations