© 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. 13993
    Prev
    Next
    INDEX
    Explanations

    Toyota Avensis D-4D

    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
     un
    -0.20
    er
    -0.20
    -
    -0.19
     odd
    -0.19
    âĢ³
    -0.19
    aren
    -0.18
    als
    -0.18
    .pojo
    -0.18
    ·
    -0.18
     (
    -0.18
    POSITIVE LOGITS
     Mobility
    0.20
    çľ¼æ³ª
    0.19
    骧
    0.19
     Canary
    0.18
    é¡¿
    0.18
    	TokenName
    0.18
    ç»ĻåĬĽ
    0.18
     Crash
    0.18
    -heading
    0.18
     limburg
    0.17
    Activations Density 0.047%

    No Known Activations