© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12473
    Prev
    Next
    INDEX
    Explanations

    felt-like or felt-lined

    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
    aben
    -0.17
    ä¹İ
    -0.17
    橹
    -0.17
    _timing
    -0.16
    ç±³ç²ī
    -0.16
    onde
    -0.16
    è¡©
    -0.16
    ãģ¶ãĤĬ
    -0.16
     Francois
    -0.16
    ity
    -0.15
    POSITIVE LOGITS
    åĪ¶åĵģ
    0.24
    ed
    0.23
    åĵģå¾·
    0.19
    icated
    0.18
    åĪ¶æĪIJ
    0.18
    çĮľ
    0.18
    emes
    0.18
    èĪĪ趣
    0.17
    entes
    0.17
    making
    0.17
    Activations Density 0.003%

    No Known Activations