© 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. 15489
    Prev
    Next
    INDEX
    Explanations

    som with prefixes or suffixes

    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
    emption
    -0.19
     Heb
    -0.16
    çİij
    -0.15
    cter
    -0.15
    å©¿
    -0.15
    rä
    -0.15
    uard
    -0.15
    è°Ł
    -0.15
    /cop
    -0.15
    rador
    -0.15
    POSITIVE LOGITS
    »
    0.20
    platz
    0.18
    place
    0.17
    ality
    0.16
    ãĥĮ
    0.16
    个å¤ļ
    0.16
    çĦ¶æĺ¯
    0.15
    esthetic
    0.15
    rio
    0.15
    ewhat
    0.15
    Activations Density 0.030%

    No Known Activations