© 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. 15677
    Prev
    Next
    INDEX
    Explanations

    is distributed

    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
    éĢļ
    -0.20
    CallableWrapper
    -0.20
    æħİ
    -0.19
     sort
    -0.19
    FK
    -0.18
     gent
    -0.18
    obot
    -0.18
    纪
    -0.18
    gMaps
    -0.18
    注éĩį
    -0.18
    POSITIVE LOGITS
    ä½ľåĵģåĨħ容
    0.19
    çĺ¢
    0.19
    èµ°åĬ¿
    0.19
    yper
    0.19
    åĴ»
    0.18
     Whisper
    0.18
    æħĭ度
    0.18
    å¦ĵ
    0.18
    èģĭ
    0.18
    诽
    0.18
    Activations Density 0.189%

    No Known Activations