© 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. 11903
    Prev
    Next
    INDEX
    Explanations

    image source attributions

    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
    (Application
    -0.21
    .compareTo
    -0.20
    Fashion
    -0.19
     зÑĢ
    -0.19
    ết
    -0.19
    ç¿°
    -0.19
    бол
    -0.19
    Ĥæķ°
    -0.18
    ŀ
    -0.18
    reu
    -0.18
    POSITIVE LOGITS
    çīĪæĿĥå½ĴåİŁ
    0.21
    åħ¥åĽŃ
    0.21
     ©
    0.21
    å¦Ĥæľīä¾µæĿĥ
    0.21
    aph
    0.20
    æĵħ
    0.20
    åıĹ访èĢħ
    0.20
     sut
    0.19
    åı¯çĶ¨äºİ
    0.19
    è·ŁæĪij说
    0.19
    Activations Density 0.019%

    No Known Activations