© 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. 15094
    Prev
    Next
    INDEX
    Explanations

    when you

    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
     hadn
    -0.23
    æĽ¾
    -0.21
    ermen
    -0.21
    erm
    -0.20
    ä¸ĢçĽ´æ²¡æľī
    -0.20
    æ°
    -0.19
     ''
    -0.19
    ba
    -0.19
     was
    -0.19
     earlier
    -0.19
    POSITIVE LOGITS
    置身
    0.21
    éĺħ读åħ¨æĸĩ
    0.19
    _sphere
    0.19
     exce
    0.18
    LEY
    0.18
    åĵ¡
    0.18
    çķĻæĦı
    0.18
    кÑĢо
    0.18
    ibre
    0.18
    _signed
    0.18
    Activations Density 0.053%

    No Known Activations