© 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. 13356
    Prev
    Next
    INDEX
    Explanations

    occurrences

    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
    rock
    -0.20
    iator
    -0.17
     Ñģобой
    -0.17
    coins
    -0.16
    æĥħæĢĢ
    -0.16
    istas
    -0.16
    omics
    -0.16
    æ¹ĸåĮº
    -0.16
    ðŁı»
    -0.16
    ä¸ĬãģĴ
    -0.16
    POSITIVE LOGITS
    uate
    0.17
    asions
    0.17
    iginal
    0.16
    abinet
    0.16
    eel
    0.16
    ption
    0.15
    apture
    0.15
    alesce
    0.15
    rypted
    0.15
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.15
    Activations Density 0.042%

    No Known Activations