© 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. 13978
    Prev
    Next
    INDEX
    Explanations

    waiting

    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
     cover
    -0.22
     trimest
    -0.19
     fours
    -0.19
     scop
    -0.19
     Freel
    -0.18
    éļĪ
    -0.18
    cover
    -0.18
     sph
    -0.18
     Haupt
    -0.18
     endanger
    -0.18
    POSITIVE LOGITS
    çŃīå¾ħ
    0.54
    æİĴéĺŁ
    0.52
    çŃīåĢĻ
    0.48
     waiting
    0.42
     wait
    0.39
    waiting
    0.38
    .wait
    0.37
     waits
    0.36
    wait
    0.36
    Waiting
    0.36
    Activations Density 0.103%

    No Known Activations