© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12274
    Prev
    Next
    INDEX
    Explanations

    hexadecimal constants and parameters

    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
    æĶ¶å®ĺ
    -0.23
    PELL
    -0.21
    alley
    -0.21
    bedo
    -0.19
    tep
    -0.18
    è¿Ļæĸ¹éĿ¢
    -0.18
    åħ¨éĿ¢
    -0.18
    çĿ¦
    -0.18
    olib
    -0.17
    iple
    -0.17
    POSITIVE LOGITS
    çĻ»
    0.19
    ä¸ŃåĽ½æ¢¦
    0.18
    ढ
    0.18
    åħ±åIJĮåıijå±ķ
    0.18
    gether
    0.18
    åıijå±ķåīįæĻ¯
    0.18
    appers
    0.18
     normalization
    0.17
    ä½ľåĵģåĨħ容
    0.17
    ATED
    0.17
    Activations Density 0.001%

    No Known Activations