© 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. 11172
    Prev
    Next
    INDEX
    Explanations

    rare day, earth, instances, exceptions, clinical, looks

    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
    大å±Ģ
    -0.17
    erna
    -0.17
    urma
    -0.16
     Äijỡ
    -0.16
    unkt
    -0.16
    serter
    -0.16
    sWith
    -0.16
    [in
    -0.15
    rade
    -0.15
    ssel
    -0.15
    POSITIVE LOGITS
    faction
    0.30
    à¹Ĩ
    0.22
    té
    0.22
    hood
    0.20
    ness
    0.19
     جدا
    0.19
    ball
    0.19
    theless
    0.19
    gram
    0.18
    pedia
    0.18
    Activations Density 0.016%

    No Known Activations