© 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. 16885
    Prev
    Next
    INDEX
    Explanations

    to indicating or relation

    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
    缴éĢļ车
    -0.22
    ä¹Łå¾Ī
    -0.22
    å´¤
    -0.21
     Dana
    -0.21
    人们çļĦ
    -0.20
    ubit
    -0.19
    è·Ĥ
    -0.19
    unct
    -0.19
    们éĥ½
    -0.18
     repro
    -0.18
    POSITIVE LOGITS
    åİī
    0.23
    对该
    0.20
    æĶ¾å¼ĥ
    0.20
    å°Ĩä¼ļ
    0.20
    ousel
    0.19
    _cookie
    0.19
    LAY
    0.19
    å°Ĩ以
    0.19
     Dangerous
    0.19
    _pressed
    0.19
    Activations Density 0.028%

    No Known Activations