© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    joy of

    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
    avis
    -0.16
    ORAGE
    -0.16
    åķĨä¼ļ
    -0.15
    romise
    -0.15
    çĹħæĥħ
    -0.15
    /OR
    -0.15
     vice
    -0.15
    jab
    -0.15
    åī¯å±Ģéķ¿
    -0.14
    ä¸ĢåĽŀäºĭ
    -0.14
    POSITIVE LOGITS
    fully
    0.41
    ful
    0.28
    fulness
    0.27
    ly
    0.23
    FUL
    0.21
    绪
    0.20
    ride
    0.20
    ably
    0.19
    iest
    0.19
    ingly
    0.18
    Activations Density 0.021%

    No Known Activations