© 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. 16704
    Prev
    Next
    INDEX
    Explanations

    numbers with punctuation

    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
    scr
    -0.17
    ģ
    -0.16
    еÑĢи
    -0.16
    ãģĤãĤĭ
    -0.16
    ees
    -0.15
    hip
    -0.15
    ç§įç±»
    -0.15
    ublic
    -0.15
     fort
    -0.15
    fono
    -0.15
    POSITIVE LOGITS
    teenth
    0.29
    ties
    0.29
    деÑģÑıÑĤ
    0.26
    ষ
    0.24
    ../../../
    0.21
    ç¿®
    0.21
    èĻ¹æ¡¥
    0.20
    å¼¢
    0.19
    teen
    0.18
    apos
    0.18
    Activations Density 0.581%

    No Known Activations