© 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. 13600
    Prev
    Next
    INDEX
    Explanations

    Sch followed by names and words

    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
    orary
    -0.19
    Ñĩик
    -0.18
    ção
    -0.17
    eous
    -0.17
    itive
    -0.17
    gether
    -0.17
    auce
    -0.16
    ized
    -0.16
    idad
    -0.16
    ัà¸ģษ
    -0.16
    POSITIVE LOGITS
    pedia
    0.20
    intosh
    0.20
    ãģĹãģ¾ãģĦ
    0.17
    usters
    0.16
    itect
    0.16
    «
    0.16
    midt
    0.16
    pire
    0.15
    inet
    0.15
    LER
    0.15
    Activations Density 0.033%

    No Known Activations