© 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. 10715
    Prev
    Next
    INDEX
    Explanations

    various quantities or types

    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
     ведÑĮ
    -0.21
    åIJĮä¸Ģ个
    -0.18
     Bol
    -0.18
    ako
    -0.17
    积æŀģæݢ索
    -0.17
    ello
    -0.17
     Sole
    -0.17
     bol
    -0.17
    åĨ·åį´
    -0.17
    éħ·
    -0.16
    POSITIVE LOGITS
    gere
    0.21
    FTA
    0.20
     Erg
    0.20
    pons
    0.18
    缸åºĶ
    0.18
     poste
    0.18
    缸åºĶçļĦ
    0.18
    å°½
    0.17
    éļıä¹ĭ
    0.17
    eous
    0.17
    Activations Density 0.110%

    No Known Activations