© 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. 14155
    Prev
    Next
    INDEX
    Explanations

    optical system and lens focusing

    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
    ENCES
    -0.20
    enties
    -0.19
    arra
    -0.19
    éĺķ
    -0.19
    omens
    -0.19
    bish
    -0.19
    æ¯ı人
    -0.18
    деж
    -0.18
    peg
    -0.18
    aviors
    -0.18
    POSITIVE LOGITS
    åħīåѦ
    0.23
     optics
    0.22
     lens
    0.20
    åħī
    0.20
    ç»Ĵ
    0.19
    åı£å¾Ħ
    0.19
    设计
    0.19
     uten
    0.19
    åѦåŃIJ
    0.18
    q
    0.18
    Activations Density 0.088%

    No Known Activations