© 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. 16729
    Prev
    Next
    INDEX
    Explanations

    past tense verb then location/time/description

    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
    éĨį
    -0.25
    æµļ
    -0.25
    æķĿ
    -0.24
     feedback
    -0.23
     system
    -0.23
     bandwidth
    -0.23
     power
    -0.22
     review
    -0.21
     target
    -0.21
     dikke
    -0.21
    POSITIVE LOGITS
    è®°è½½
    0.30
    çĻ»è®°
    0.29
    æĿĤ
    0.28
     Possibly
    0.27
    possibly
    0.26
     presumably
    0.26
     possibly
    0.26
    游æĪı代
    0.26
    å±ħä½ı
    0.26
    çĸijä¼¼
    0.25
    Activations Density 0.184%

    No Known Activations