© 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. 13557
    Prev
    Next
    INDEX
    Explanations

    curated, monograph, specification, management, Q:, Kiwanis

    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
    ãĤŃãĥ£ãĥ³ãĥļ
    -0.24
    ichick
    -0.24
    ãĤ¢ãĤ¤ãĥĨ
    -0.24
    ãĤ¢ãĥ¡ãĥª
    -0.23
    æīĢæľīæĥħèĬĤ
    -0.23
    ãĥijãĥijæ´»
    -0.23
    ÑĢеги
    -0.23
    迪士
    -0.22
    便æ°ij
    -0.22
    благо
    -0.22
    POSITIVE LOGITS
    空éĹ´
    0.25
    Fuck
    0.24
    ç¾İæľ¯é¦Ĩ
    0.23
     spaces
    0.23
     space
    0.23
    èīºæľ¯å®¶
    0.22
    Spaces
    0.22
    bsite
    0.22
    çĶ°éĩİ
    0.22
    è±Ĩçĵ£
    0.22
    Activations Density 0.097%

    No Known Activations