© 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. 13373
    Prev
    Next
    INDEX
    Explanations

    license file

    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
     tails
    -0.20
    ä¸įçķĻ
    -0.20
    ãĤº
    -0.20
    éĢıæĺİ
    -0.20
    Decorator
    -0.19
     tail
    -0.19
    gettext
    -0.18
    EOF
    -0.18
    åħ¬å®īéĥ¨
    -0.18
    å°±æĪIJäºĨ
    -0.18
    POSITIVE LOGITS
    Syn
    0.19
    syn
    0.19
    pis
    0.18
    libc
    0.17
    caffold
    0.17
    éĿ¡
    0.17
    oola
    0.17
    aN
    0.17
     Holl
    0.17
    icates
    0.17
    Activations Density 0.012%

    No Known Activations