© 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. 16431
    Prev
    Next
    INDEX
    Explanations

    act dead or as

    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
    vida
    -0.21
    çľ¼æ³ª
    -0.20
    atin
    -0.20
    ãģŁãģı
    -0.20
    åĽłä¸ºåľ¨
    -0.18
    ä½Ĩä¸įéĻIJ
    -0.18
    éķ¿éķ¿çļĦ
    -0.17
    uges
    -0.17
    atan
    -0.16
    ÑĢÑĥд
    -0.16
    POSITIVE LOGITS
    uate
    0.30
    IVATE
    0.21
    DrawerToggle
    0.21
    ively
    0.20
    /be
    0.19
    /respond
    0.19
    uated
    0.18
    uating
    0.18
    âĹ»
    0.18
    伪
    0.17
    Activations Density 0.020%

    No Known Activations