© 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. 11000
    Prev
    Next
    INDEX
    Explanations

    names have been changed

    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
    æĥ³ä¸įåĪ°
    -0.21
    _REGS
    -0.20
    è½±
    -0.19
    çīĴ
    -0.19
    çŃ¾
    -0.19
    ä¸įåıĬ
    -0.18
    çģµæ°Ķ
    -0.18
    æľīèĥ½åĬĽ
    -0.18
    å½Ģ
    -0.17
    _PRINTF
    -0.17
    POSITIVE LOGITS
    amarin
    0.22
    æ²ī浸
    0.20
    çijĽ
    0.19
    ÑĢÑĥÑģ
    0.19
    æľ«
    0.19
    以åħį
    0.18
    æģ¯
    0.18
    Certain
    0.18
    æıIJ款
    0.18
    å°±æĺ¯åĽłä¸º
    0.18
    Activations Density 0.005%

    No Known Activations