© 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. 16386
    Prev
    Next
    INDEX
    Explanations

    which

    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
    说æĺ¯
    -0.21
    anche
    -0.17
    thon
    -0.17
    çĤ¹äºĨ
    -0.17
    yar
    -0.17
    culus
    -0.16
    ideographic
    -0.16
    _EXTERN
    -0.16
    ulu
    -0.16
    anches
    -0.15
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.24
     suá»ijt
    0.20
    /out
    0.19
    çĶŁæ´»çļĦ
    0.19
    è´¨éĩıåĴĮ
    0.18
    haled
    0.18
    人éĥ½
    0.18
    oret
    0.17
    lies
    0.17
    pres
    0.17
    Activations Density 0.028%

    No Known Activations