© 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. 13269
    Prev
    Next
    INDEX
    Explanations

    state of the art equipment

    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
    MBOL
    -0.20
    建议
    -0.20
    hare
    -0.20
    -us
    -0.20
    æī¹åıij
    -0.20
    å®īæĬļ
    -0.20
    arus
    -0.20
    åĨĴ
    -0.19
    rule
    -0.19
    建èŃ°
    -0.19
    POSITIVE LOGITS
     equipment
    0.32
    设å¤ĩ
    0.30
    éĺµå®¹
    0.30
    设æĸ½
    0.29
    åħĪè¿ĽçļĦ
    0.28
    éħįå¤ĩ
    0.28
    è£ħå¤ĩ
    0.28
    equipment
    0.27
    è¿Ļå¥Ĺ
    0.26
    使çĶ¨çļĦ
    0.26
    Activations Density 0.046%

    No Known Activations