© 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. 15344
    Prev
    Next
    INDEX
    Explanations

    contact information and phone numbers

    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
    æĸ°åĨľæĿij
    -0.24
    rovers
    -0.23
    åĽŀæĿ¥äºĨ
    -0.20
    é¡»
    -0.19
    æĤłä¹ħ
    -0.19
     Tá»Ń
    -0.18
    procs
    -0.18
    å½¹
    -0.18
    èĢģé¾ĦåĮĸ
    -0.18
    éĵ®
    -0.18
    POSITIVE LOGITS
    ä»ĸèĩªå·±
    0.21
    åĴķ
    0.19
    ouro
    0.18
     filing
    0.18
     LinkedIn
    0.17
     email
    0.17
    IEL
    0.17
    ué
    0.17
     Berkeley
    0.17
     gro
    0.17
    Activations Density 0.017%

    No Known Activations