© 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. 13558
    Prev
    Next
    INDEX
    Explanations

    code comment delimiters

    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
    owler
    -0.21
    Readable
    -0.20
     coached
    -0.19
    èĮĮ
    -0.18
     habit
    -0.18
    camel
    -0.17
    ê¼´
    -0.17
    à¸Ĭะ
    -0.17
    æ´¸
    -0.17
     Robertson
    -0.17
    POSITIVE LOGITS
    æĻļæľŁ
    0.22
    佩æĪ´
    0.21
    å®ģå¤ı
    0.20
    æĻ¦
    0.20
    æĻ·
    0.20
     Marriott
    0.20
    ç¦ģå¿Į
    0.19
    éĶ±
    0.19
    æ±īåŃIJ
    0.19
    ç¦ģæŃ¢
    0.19
    Activations Density 0.003%

    No Known Activations