© 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. 16678
    Prev
    Next
    INDEX
    Explanations

    Red Hat Linux Enterprise

    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
     uLocal
    -0.20
    eways
    -0.19
    ClientRect
    -0.18
    _ROUT
    -0.18
    /entities
    -0.18
    pirit
    -0.18
     photos
    -0.18
     Colonial
    -0.18
    å©Ĩ
    -0.18
     Yap
    -0.18
    POSITIVE LOGITS
    åķĨåĵģ
    0.22
     Morrow
    0.21
    åĵĪå°Ķ
    0.20
    æĸ¯åŁº
    0.20
    brew
    0.20
    ä¸ŃæľŁ
    0.20
    rpm
    0.19
    paid
    0.19
     LINUX
    0.19
    sys
    0.19
    Activations Density 0.043%

    No Known Activations