© 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. 15502
    Prev
    Next
    INDEX
    Explanations

    surrounding punctuation in code or text

    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
    lah
    -0.18
    наÑĩ
    -0.18
    ially
    -0.16
    NotNull
    -0.16
    curring
    -0.16
    ele
    -0.16
    éĢļçķħ
    -0.15
    ÙĦÙĬب
    -0.15
    é¹Ĺ
    -0.15
    ä¸ĩåįĥ
    -0.15
    POSITIVE LOGITS
    a
    0.23
    o
    0.21
    oftware
    0.21
    i
    0.21
    า
    0.20
    alysis
    0.19
    è·¯ä¸Ĭ
    0.18
    anford
    0.18
    人
    0.18
    �
    0.18
    Activations Density 0.246%

    No Known Activations