© 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. 12992
    Prev
    Next
    INDEX
    Explanations

    until you/with/strapped

    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
    æĪij没æľī
    -0.26
    _dbg
    -0.22
    immer
    -0.20
     baÅŁarı
    -0.20
    éħ¿
    -0.20
    æ¶Ŀ
    -0.20
    èĶº
    -0.19
    _SAN
    -0.18
    åıijè´¢
    -0.18
    бил
    -0.18
    POSITIVE LOGITS
    å®ĥçļĦ
    0.25
    åıĤä¸İ
    0.22
    çľĭè¿ĩ
    0.22
     rub
    0.21
    å®ĥ
    0.21
    çľĭ
    0.20
    对æ¯Ķ
    0.20
    åıĤä¸İåĪ°
    0.20
    çľĭä»ĸ
    0.20
    phin
    0.20
    Activations Density 0.034%

    No Known Activations