© 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. 16549
    Prev
    Next
    INDEX
    Explanations

    jump into action

    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
    å¾Īéķ¿
    -0.21
    ylie
    -0.19
    è¯Ŀè¯Ń
    -0.18
    .soft
    -0.18
    åģľçķĻ
    -0.18
    ascar
    -0.17
    累累
    -0.17
    izia
    -0.16
    å¢ĥåĨħ
    -0.16
    hape
    -0.16
    POSITIVE LOGITS
    frog
    0.21
    dez
    0.20
    蹦
    0.20
    åĴİ
    0.19
    into
    0.19
    è§ĸ
    0.19
    eded
    0.18
    RoleId
    0.18
    pon
    0.18
     into
    0.18
    Activations Density 0.019%

    No Known Activations