© 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. 14794
    Prev
    Next
    INDEX
    Explanations

    two related factors/systems

    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
    èļĮ
    -0.19
    okin
    -0.18
    ä¸ī人
    -0.18
    ãģ¯ãĤĤãģ¡ãĤįãĤĵ
    -0.18
    æĮĩ导ä¸ĭ
    -0.18
    isle
    -0.17
    edm
    -0.17
     octave
    -0.17
    äºļ太
    -0.17
     ABI
    -0.17
    POSITIVE LOGITS
    两èĢħ
    0.58
    äºĮèĢħ
    0.55
    è¿Ļ两个
    0.48
    è¿Ļ两
    0.46
    è¿Ļ两ç§į
    0.46
    两项
    0.41
    ç»ĵåIJĪèµ·æĿ¥
    0.40
    åīįèĢħ
    0.39
    缸ç»ĵåIJĪ
    0.35
    åıĮéĩį
    0.34
    Activations Density 0.609%

    No Known Activations