© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12513
    Prev
    Next
    INDEX
    Explanations

    grade, -made, -size

    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
    _ING
    -0.17
    jni
    -0.17
    IQ
    -0.17
    lore
    -0.17
    缮åīį
    -0.17
    ittel
    -0.17
    iverse
    -0.17
    ä¸Ģå¼ł
    -0.17
    å±ī
    -0.17
    çİ°åľ¨å¾Īå¤ļ
    -0.16
    POSITIVE LOGITS
    åĮºåŁŁæĢ§
    0.24
    éĽĨä½ĵ
    0.23
    åħ¨æĹ¥
    0.21
    ä¸İæĹ¶ä¿±
    0.20
    æĸ¹å¼ıè¿Ľè¡Į
    0.20
    cone
    0.19
    åıĮåIJij
    0.19
    æ²»
    0.18
     HM
    0.18
    ãģĤãĤĮ
    0.18
    Activations Density 0.449%

    No Known Activations