© 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. 14534
    Prev
    Next
    INDEX
    Explanations

    fixed amount or dose

    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
    ÑģоÑģ
    -0.20
    èĢĥè¯ģ
    -0.20
    åħħåĪĨ
    -0.19
    zem
    -0.19
    _CA
    -0.18
    Ñħодим
    -0.18
    é¼ł
    -0.17
     Filip
    -0.17
    AMA
    -0.17
    é½IJ
    -0.17
    POSITIVE LOGITS
    åĽºå®ļçļĦ
    0.35
    åĽºå®ļ
    0.33
     fixed
    0.31
    -fixed
    0.31
    /static
    0.30
    .Fixed
    0.29
     Fixed
    0.29
    æŶéĹ´åĨħ
    0.28
    Fixed
    0.28
    ä¸įåıĺ
    0.26
    Activations Density 0.112%

    No Known Activations