© 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. 13911
    Prev
    Next
    INDEX
    Explanations

    Source License Site

    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
    erval
    -0.25
    åģļ强
    -0.23
    严éĩį
    -0.21
    RTOS
    -0.19
    genome
    -0.19
    óng
    -0.19
    rig
    -0.18
    idar
    -0.18
    ritt
    -0.18
    ëĭĿ
    -0.18
    POSITIVE LOGITS
    ayout
    0.19
    eko
    0.18
    好好
    0.18
    è¾ĪåŃIJ
    0.18
    æĭIJ
    0.17
    ç³ľ
    0.17
    tml
    0.17
    以èī²åĪĹ
    0.17
    _bits
    0.16
    ç»Ī身
    0.16
    Activations Density 0.004%

    No Known Activations