© 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. 13642
    Prev
    Next
    INDEX
    Explanations

    temperature and units

    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
    heid
    -0.20
    å®£ä¼łæ´»åĬ¨
    -0.20
    缸è¿ŀ
    -0.20
    交éĢļ
    -0.19
    ä¿®çIJĨ
    -0.19
    å®Ľ
    -0.18
    Spatial
    -0.18
    宣åijĬ
    -0.18
    ink
    -0.18
    isObject
    -0.17
    POSITIVE LOGITS
    温度
    0.20
    rosis
    0.19
    ernals
    0.18
    çĥ§
    0.18
    _Class
    0.18
    .temperature
    0.18
    omain
    0.18
    keepers
    0.17
    andex
    0.17
    Fant
    0.17
    Activations Density 0.006%

    No Known Activations