© 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. 12887
    Prev
    Next
    INDEX
    Explanations

    styling, state, functionality, data

    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
    <tag
    -0.21
    fatal
    -0.20
    èĥ½æĬĬ
    -0.19
    ç¬ı
    -0.19
    >tag
    -0.19
    å´Ľèµ·
    -0.18
    .pnl
    -0.18
    室åĨħ
    -0.18
    åĬ©éķ¿
    -0.18
    redd
    -0.18
    POSITIVE LOGITS
    åİŁæĿ¥
    0.32
     intact
    0.31
    åİŁæĿ¥çļĦ
    0.28
    åİŁæľīçļĦ
    0.26
     originally
    0.25
    Already
    0.25
    åİŁä¾Ĩ
    0.25
     unchanged
    0.24
    ä¸įåıĺ
    0.23
    Same
    0.23
    Activations Density 0.428%

    No Known Activations