© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15395
    Prev
    Next
    INDEX
    Explanations

    crates, carriers, packages

    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
    icut
    -0.18
    åĭº
    -0.18
    åĪ¶çº¦
    -0.18
    鼶ç¢İ
    -0.18
    su
    -0.17
    som
    -0.17
    è¡Ĺä¸Ĭ
    -0.17
    sWith
    -0.17
    uate
    -0.17
    vak
    -0.17
    POSITIVE LOGITS
    lama
    0.18
    æĭ¯
    0.18
    elor
    0.17
    lijk
    0.16
    riers
    0.16
    yard
    0.15
    ä½
    0.15
    ãģĽãģ¦
    0.15
    lash
    0.15
    ty
    0.15
    Activations Density 0.001%

    No Known Activations