© 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. 12954
    Prev
    Next
    INDEX
    Explanations

    unknown or other

    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
    æĶ»çķ¥
    -0.21
    urf
    -0.21
    _guide
    -0.20
    åIJĮæŃ¥
    -0.19
    ä¸ĭ游
    -0.19
     singles
    -0.18
    lifetime
    -0.18
    isphere
    -0.18
    gettext
    -0.17
    åīįè¿Ľ
    -0.17
    POSITIVE LOGITS
    .Unknown
    0.27
    æľªçŁ¥
    0.25
    åĪĽæĸ°åŀĭ
    0.24
     Unknown
    0.23
     unknown
    0.23
     exotic
    0.22
    Unknown
    0.22
     lạ
    0.20
    LEAN
    0.19
    .UNKNOWN
    0.19
    Activations Density 0.131%

    No Known Activations