© 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. 15223
    Prev
    Next
    INDEX
    Explanations

    pros and prospects

    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
    oder
    -0.18
    maal
    -0.18
    па
    -0.17
    yps
    -0.17
    OrUpdate
    -0.17
    orem
    -0.17
    ä¸įäºĨ
    -0.17
    èµ°å¾Ĺ
    -0.17
    ä¸įå®ī
    -0.17
    hips
    -0.17
    POSITIVE LOGITS
    ðŁı»
    0.22
    ðŁı¼
    0.18
    à¹Ĩ
    0.18
    entially
    0.17
    ctors
    0.17
     à¹Ĩ
    0.17
     иÑģполÑĮзованиÑı
    0.17
    ðŁı½
    0.16
     versa
    0.16
    çĦ±
    0.16
    Activations Density 0.010%

    No Known Activations