© 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. 16935
    Prev
    Next
    INDEX
    Explanations

    rounds of competition

    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
    alem
    -0.20
    åģ·
    -0.20
    强壮
    -0.20
    atra
    -0.19
    yaw
    -0.19
     variant
    -0.19
     scarc
    -0.19
    _contin
    -0.18
    ä»İæł¹æľ¬ä¸Ĭ
    -0.18
    驹
    -0.18
    POSITIVE LOGITS
     ÑįÑĤап
    0.23
    éĺ¶æ®µ
    0.22
     stage
    0.22
    è¾Ħ
    0.21
    stage
    0.20
    _STAGE
    0.20
    pline
    0.20
    ä¼ļå±ķ
    0.20
     étape
    0.19
     Stage
    0.19
    Activations Density 0.033%

    No Known Activations