© 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. 16801
    Prev
    Next
    INDEX
    Explanations

    bold text formatting

    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
    mares
    -0.20
    oldt
    -0.20
    太太
    -0.20
    çĽijåIJ¬é¡µéĿ¢
    -0.19
    ModuleName
    -0.19
    reas
    -0.19
    .Listen
    -0.18
    alysis
    -0.18
    æ¬
    -0.18
    OTES
    -0.17
    POSITIVE LOGITS
    ness
    0.20
    æĹłç¼ĺ
    0.19
     Gulf
    0.18
    æķĪæŀľ
    0.18
    íĥľ
    0.18
    强度
    0.18
    çŃī级
    0.18
     edx
    0.18
     boost
    0.18
    prime
    0.17
    Activations Density 0.063%

    No Known Activations