© 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. 16826
    Prev
    Next
    INDEX
    Explanations

    MTV and related abbreviations

    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
    loom
    -0.24
    æĺ¼
    -0.18
     ventil
    -0.18
    豸
    -0.18
    chaft
    -0.18
    clipse
    -0.17
    é²ł
    -0.17
    å±Ģéķ¿
    -0.17
    媳å¦ĩ
    -0.16
    ми
    -0.16
    POSITIVE LOGITS
    avn
    0.19
    tere
    0.18
    verse
    0.18
    éré
    0.18
    ope
    0.18
    ikon
    0.18
    æĦŁæŁĵ
    0.17
     Pavilion
    0.17
     Eins
    0.17
    ér
    0.16
    Activations Density 0.002%

    No Known Activations