© 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. 12090
    Prev
    Next
    INDEX
    Explanations

    project, reinforcement, launch, provide

    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»ĬæĻļ
    -0.29
    oze
    -0.27
    ä½łçİ°åľ¨
    -0.25
    abee
    -0.25
    zie
    -0.24
     tonight
    -0.24
    çľĭä½ł
    -0.24
    åĪ°æŶåĢĻ
    -0.24
    çĪ¸çĪ¸å¦Īå¦Ī
    -0.23
    ä½łåºĶ该
    -0.23
    POSITIVE LOGITS
    åı¯æĥ³èĢĮ
    0.27
    ðŁĺ£
    0.25
    ðŁĻģ
    0.25
    æĢ»èĢĮè¨Ģ
    0.25
    å°ıå¿ĥ翼
    0.24
    ðŁĺij
    0.24
    å·§åħĭ
    0.24
    æ¯ıæľĪ
    0.24
    ðŁĺĵ
    0.23
     vendor
    0.23
    Activations Density 0.084%

    No Known Activations