© 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. 14231
    Prev
    Next
    INDEX
    Explanations

    passage 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
    åŀ´
    -0.23
    亲è¿ij
    -0.21
    éĶ¯
    -0.19
    atif
    -0.18
    rones
    -0.18
    enerative
    -0.18
    sons
    -0.18
    ç°Į
    -0.18
    iaux
    -0.18
    iev
    -0.18
    POSITIVE LOGITS
    ç©¿è¿ĩ
    0.32
    ç©¿éĢı
    0.27
    ç©¿
    0.26
    éĢı
    0.24
    ç©¿è¶Ĭ
    0.24
     passage
    0.23
    ç©¿æ¢Ń
    0.23
     passes
    0.23
     passing
    0.22
    è¿ĩçļĦ
    0.22
    Activations Density 0.229%

    No Known Activations