© 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. 14517
    Prev
    Next
    INDEX
    Explanations

    names after "by"

    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
    èĵĦ
    -0.19
     surprising
    -0.18
    åŀĴ
    -0.18
    _conditions
    -0.18
    æĮĤ
    -0.17
    çļĦæľ¬è´¨
    -0.17
    ymes
    -0.17
    esktop
    -0.17
    IVA
    -0.17
    egas
    -0.17
    POSITIVE LOGITS
    èĪįå¾Ĺ
    0.22
    ç¿»è¯ij
    0.21
    åı¯èĥ½åŃĺåľ¨
    0.20
    æķ´çIJĨ
    0.20
    çĪ±å°Ķ
    0.20
    å·¥ç¨ĭæĬĢæľ¯
    0.18
    cco
    0.18
    主ä¹īèĢħ
    0.18
    .Assert
    0.17
    欢è¿İæĤ¨
    0.17
    Activations Density 0.010%

    No Known Activations