© 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. 11662
    Prev
    Next
    INDEX
    Explanations

    monopoly or singleton

    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
    å±ħ室
    -0.19
    éľ²
    -0.16
    éłĨ
    -0.16
    oped
    -0.16
    work
    -0.15
    works
    -0.15
     кол
    -0.15
    esthes
    -0.15
    iddle
    -0.15
    inning
    -0.15
    POSITIVE LOGITS
    æĢ§çļĦ
    0.19
    èĢħçļĦ
    0.18
    iar
    0.18
    æĪĸå¤ļ
    0.17
    tero
    0.17
    /un
    0.17
    orea
    0.17
    aires
    0.17
    erta
    0.17
    å²Į
    0.16
    Activations Density 0.006%

    No Known Activations