© 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. 14134
    Prev
    Next
    INDEX
    Explanations

    cleaning agents and substances

    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
    éķĬ
    -0.23
    mma
    -0.23
    èĮĦåŃIJ
    -0.20
    igue
    -0.19
    irs
    -0.19
    æĴ©
    -0.19
    .MM
    -0.19
    ells
    -0.18
    nets
    -0.18
    borg
    -0.18
    POSITIVE LOGITS
    æ¡·
    0.21
    Spl
    0.20
     spl
    0.20
    NullOrEmpty
    0.20
    agr
    0.19
    spl
    0.19
    æ±ģ
    0.18
    URAL
    0.18
    pod
    0.17
     Born
    0.17
    Activations Density 0.016%

    No Known Activations