© 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. 12791
    Prev
    Next
    INDEX
    Explanations

    java, android, or go package names

    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
    çĸĻ
    -0.21
     INCIDENT
    -0.21
    ToOne
    -0.20
    ä¸ĢçĶŁ
    -0.20
    íĬ¼
    -0.19
    _HOOK
    -0.18
    .subplots
    -0.18
    ÃľN
    -0.18
    å¼ĵ
    -0.18
     же
    -0.18
    POSITIVE LOGITS
     giveaway
    0.20
    æĿĤ
    0.19
    reason
    0.18
    鼾
    0.17
     distraction
    0.17
    å¼Ħ
    0.17
     cherry
    0.17
    æĻĵ
    0.17
     Gravity
    0.17
    -posts
    0.17
    Activations Density 0.199%

    No Known Activations