© 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. 12632
    Prev
    Next
    INDEX
    Explanations

    email header markers

    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
    åijĬ
    -0.22
    åij½
    -0.20
    gie
    -0.19
     kê
    -0.19
    è¿ĺæĺ¯å¾Ī
    -0.19
    lot
    -0.19
    èĥ³èĨĬ
    -0.19
    che
    -0.18
    Ng
    -0.18
    KA
    -0.18
    POSITIVE LOGITS
    .stamp
    0.20
    äºĶéĩij
    0.19
    istogram
    0.18
    ultipart
    0.18
    éĥ¢
    0.18
    çĺ°
    0.18
    IVAL
    0.18
    Designer
    0.18
    åįķ纯çļĦ
    0.18
    èĵ¬
    0.18
    Activations Density 0.019%

    No Known Activations