© 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. 15407
    Prev
    Next
    INDEX
    Explanations

    name and related identifiers

    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
    rå
    -0.23
     Prime
    -0.20
    ORLD
    -0.20
    å°ıé¾Ļ
    -0.19
    æĤī
    -0.18
    §è¡Į
    -0.18
    åľ¨çº¿åĴ¨è¯¢
    -0.18
    .infinity
    -0.18
    rated
    -0.17
    acomment
    -0.17
    POSITIVE LOGITS
     name
    0.33
    åħ·ä½ĵçļĦ
    0.29
    åIJį称
    0.29
    åIJįåŃĹ
    0.27
    åĩºå¤Ħ
    0.27
     date
    0.27
     location
    0.26
    æĺ¯è°ģ
    0.26
    ID
    0.25
    å§ĵåIJį
    0.25
    Activations Density 0.264%

    No Known Activations