© 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. 13445
    Prev
    Next
    INDEX
    Explanations

    MAV, ESC, hobby, electric

    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
    è¯
    -0.22
     trom
    -0.22
     processo
    -0.21
     Trom
    -0.19
    incinn
    -0.19
    æ°¤
    -0.19
     process
    -0.18
    chal
    -0.18
    assa
    -0.18
    utsche
    -0.18
    POSITIVE LOGITS
    é£ŀè¡Į
    0.27
    æĸ°æīĭ
    0.25
     hobby
    0.23
    çĪ±å¥½èĢħ
    0.23
    æķĻç¨ĭ
    0.22
    åıijå±ķæĸ¹åIJij
    0.22
    çĶµæľº
    0.21
    åħ¥éŨ
    0.21
    æݧåĪ¶åĻ¨
    0.20
    åĪĽå®¢
    0.20
    Activations Density 0.022%

    No Known Activations