© 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. 14383
    Prev
    Next
    INDEX
    Explanations

    every step of the way

    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
    å¾Īåĸľæ¬¢
    -0.23
    åı¦ä¸Ģç§į
    -0.21
    æľĪä¸ĭ
    -0.20
    æīĢåľ¨
    -0.19
    äºĨä¸Ģç³»åĪĹ
    -0.19
    ä¸Ģç»Ħ
    -0.19
    å¾Īæĺ¯
    -0.19
    æ¯ķç«Ł
    -0.18
    erus
    -0.18
    ä¸Ģä¸ĭ
    -0.18
    POSITIVE LOGITS
    igators
    0.19
    å®ĥ
    0.18
     Except
    0.18
    èĩªè´Ł
    0.17
    åĬªåĬĽ
    0.17
    LOUR
    0.16
     TSR
    0.16
     except
    0.16
    abay
    0.16
    nbsp
    0.16
    Activations Density 0.013%

    No Known Activations