© 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. 14592
    Prev
    Next
    INDEX
    Explanations

    Alpha Zone

    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
    ©
    -0.19
    OLUM
    -0.17
    ness
    -0.17
    illon
    -0.16
    ³
    -0.16
    èľĴ
    -0.16
    ialized
    -0.15
    ngr
    -0.15
    abouts
    -0.15
    osal
    -0.15
    POSITIVE LOGITS
    most
    0.18
    abetic
    0.16
    æĪijä¸įæĺ¯
    0.16
     tiên
    0.16
    markt
    0.15
    ine
    0.15
    oft
    0.15
    éric
    0.15
     ведÑĮ
    0.15
    EAR
    0.15
    Activations Density 0.023%

    No Known Activations