© 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. 12362
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     ÐIJлекÑģан
    -0.21
    å¤Ħå¤Ħ
    -0.19
    åIJį人
    -0.19
    游
    -0.18
    ADOR
    -0.18
     outr
    -0.18
    èĢĮåĩº
    -0.18
    对æīĭ
    -0.18
    Overall
    -0.17
    /reg
    -0.17
    POSITIVE LOGITS
    缸è¿ij
    0.21
     onwards
    0.20
    /or
    0.20
    å¾Įä¾Ĩ
    0.20
    èĨ³
    0.20
    åIJİæĿ¥
    0.20
     later
    0.20
    _REUSE
    0.19
     onward
    0.19
    phan
    0.18
    Activations Density 0.178%

    No Known Activations