© 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. 13972
    Prev
    Next
    INDEX
    Explanations

    white + noun

    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
    hip
    -0.21
    esimal
    -0.19
    ion
    -0.19
    æİĮæı¡
    -0.19
    è¡·
    -0.18
    ietf
    -0.18
    âĨµ
    -0.18
    elman
    -0.18
    ries
    -0.18
    PB
    -0.17
    POSITIVE LOGITS
    çŃ
    0.19
    稳妥
    0.19
    纱
    0.18
    æ±Ĭ
    0.18
    å±ĭåŃIJ
    0.18
    æµģæ°´
    0.18
    invert
    0.18
    ä»İä¸ļ
    0.18
    è¿ĩåħ³
    0.17
    åĬłçıŃ
    0.17
    Activations Density 0.003%

    No Known Activations