© 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. 11997
    Prev
    Next
    INDEX
    Explanations

    creating new value

    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
    æĪijèĩªå·±
    -0.25
     mostly
    -0.23
    ozo
    -0.23
    atrice
    -0.22
     Reform
    -0.22
     maybe
    -0.22
    为äºĨ让
    -0.22
     Interesting
    -0.22
    izers
    -0.21
     somewhat
    -0.21
    POSITIVE LOGITS
    æĹłç¼Ŀ
    0.30
    家åĸ»æĪ·
    0.29
     Erotische
    0.28
    æīĢæľīæĥħèĬĤ
    0.28
    æĢ»èĢĮè¨Ģ
    0.28
     tatto
    0.26
    æĤŃ
    0.26
    åĨ°æ·ĩ
    0.25
    è½»æĿ¾
    0.25
     Geile
    0.25
    Activations Density 0.090%

    No Known Activations