© 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. 13448
    Prev
    Next
    INDEX
    Explanations

    first time in years

    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
    ä¸Ģèµ·åİ»
    -0.20
    åģļèµ·
    -0.19
    _COPY
    -0.19
     oversh
    -0.18
    ä¸Ģå¼Ģå§ĭå°±
    -0.18
    æ¯Ķèµ·
    -0.18
    ä¸Ģä¸ĭåŃIJ
    -0.18
    cul
    -0.18
    èĩ³ä»Ĭ
    -0.18
    ORE
    -0.17
    POSITIVE LOGITS
    许ä¹ħ
    0.21
    _mA
    0.20
    åıĺåĬ¨
    0.20
    iola
    0.19
    frica
    0.19
    olls
    0.19
    LOTS
    0.19
    åıĺåĮĸ
    0.18
    гÑĢад
    0.18
    åĻ¤
    0.17
    Activations Density 0.019%

    No Known Activations