© 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. 11366
    Prev
    Next
    INDEX
    Explanations

    clarifying "not" or "mean"

    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
    åıªèĥ½è¯´
    -0.20
     Superior
    -0.19
    éºĤ
    -0.18
    姨
    -0.18
    ugo
    -0.18
    åĨįå¤ļ
    -0.18
    èµĪ
    -0.18
    åºķéĥ¨
    -0.18
    agination
    -0.17
     pari
    -0.17
    POSITIVE LOGITS
    éĤ£ç§į
    0.23
    seau
    0.22
    å·®åĪ«
    0.20
    åݻ买
    0.20
    çIJ³
    0.19
    åīįä¸įä¹ħ
    0.19
    置身
    0.19
    çļĦéĤ£ç§į
    0.18
    xdc
    0.18
    ä¸Ģç«Ļ
    0.18
    Activations Density 0.070%

    No Known Activations