© 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. 12338
    Prev
    Next
    INDEX
    Explanations

    photography and cinema terms

    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
    æĪĸåħ¶ä»ĸ
    -0.24
    亲
    -0.20
    cre
    -0.19
    æĬķ
    -0.19
    wizard
    -0.19
    æĪĸå¤ļæĪĸå°ij
    -0.19
    æĪĸèĢħåħ¶ä»ĸ
    -0.19
    VER
    -0.18
    èĩªçĶ±
    -0.18
    好åıĭ
    -0.18
    POSITIVE LOGITS
    ä¸ī家
    0.22
    ä¸īæĸ¹
    0.21
    çŁį
    0.21
     trilogy
    0.20
    ä¸īä½įä¸Ģä½ĵ
    0.20
    ä¸īæĿ¡
    0.19
    åĴĮ个人
    0.19
    ä¸ī人
    0.19
    оÑĢÑĤ
    0.18
    allis
    0.18
    Activations Density 0.280%

    No Known Activations