© 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. 13179
    Prev
    Next
    INDEX
    Explanations

    kit car, kit form, kit includes

    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
    sing
    -0.21
    LEX
    -0.17
    à¹Į
    -0.16
    iros
    -0.16
    mitter
    -0.16
    iction
    -0.15
    sit
    -0.15
    eur
    -0.15
    è¯Ł
    -0.15
    sse
    -0.15
    POSITIVE LOGITS
    ting
    0.21
    åŃIJéĩĮ
    0.20
    ï¸
    0.19
    rary
    0.19
    ter
    0.17
     Æ¡n
    0.17
    maker
    0.16
    ifying
    0.16
    åĤį
    0.16
    izens
    0.16
    Activations Density 0.014%

    No Known Activations