© 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. 13992
    Prev
    Next
    INDEX
    Explanations

    improved to

    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
    è¿Ŀ纪
    -0.22
    ç»°
    -0.21
    oby
    -0.21
    UBE
    -0.21
    rome
    -0.20
    æľŁéĹ´
    -0.20
    aman
    -0.20
    gar
    -0.20
    个人
    -0.19
    PathVariable
    -0.18
    POSITIVE LOGITS
    agus
    0.19
    dealloc
    0.19
     darauf
    0.19
    ãĥ©ãĥ³ãĤŃãĥ³ãĤ°
    0.18
    umper
    0.18
    æľīäºĨ
    0.18
    æĶ¶æĶ¯
    0.18
    ponsive
    0.18
    _rw
    0.17
    ç£ķ
    0.17
    Activations Density 0.014%

    No Known Activations