© 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. 12060
    Prev
    Next
    INDEX
    Explanations

    journey through

    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
    ENU
    -0.19
     mükem
    -0.19
    okable
    -0.18
    .office
    -0.18
    è¿Ļ让
    -0.18
    izzard
    -0.18
    å·¥ä½ľäººåijĺ
    -0.17
    ofday
    -0.17
    heim
    -0.17
    asha
    -0.17
    POSITIVE LOGITS
     journey
    0.33
    æĹħç¨ĭ
    0.28
    åİĨç¨ĭ
    0.28
    é¢ł
    0.26
    ç»ıåİĨ
    0.25
    åıijå±ķåİĨç¨ĭ
    0.25
    ç©¿è¶Ĭ
    0.23
    èµ·ä¼ı
    0.23
    éĢIJä¸Ģ
    0.22
     journeys
    0.22
    Activations Density 0.048%

    No Known Activations