© 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. 14791
    Prev
    Next
    INDEX
    Explanations

    presence, state, awareness, maintaining

    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
    IDES
    -0.22
    wel
    -0.19
    ExceptionHandler
    -0.18
    Needs
    -0.18
    æ¯ħ
    -0.18
     ØŃص
    -0.18
    rer
    -0.17
    åĪ°äºĨ
    -0.17
    éĿĴå¹´
    -0.17
    åıĬåħ¶
    -0.17
    POSITIVE LOGITS
    çĬ¶æĢģä¸ĭ
    0.26
     Moo
    0.21
     ÙĪبعد
    0.20
     premise
    0.20
    æĿ¡ä»¶ä¸ĭ
    0.19
    åĪĿå¿ĥ
    0.18
    èĥĮä¸Ĭ
    0.18
    åīįæıIJ
    0.18
    bpp
    0.18
    sym
    0.18
    Activations Density 0.328%

    No Known Activations