© 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. 14024
    Prev
    Next
    INDEX
    Explanations

    roll action

    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
    arend
    -0.21
    éĩı
    -0.20
    awning
    -0.18
     Lim
    -0.18
    å¿Ļ
    -0.18
    éĢ¸
    -0.18
     mut
    -0.18
    âīĤ
    -0.18
    propri
    -0.18
     prov
    -0.18
    POSITIVE LOGITS
    åĩºæĿ¥çļĦ
    0.21
    zin
    0.21
    å¢ħ
    0.20
    maid
    0.20
    æijĶ
    0.19
    æł·
    0.19
    èµ·æĿ¥äºĨ
    0.19
    stad
    0.19
    spin
    0.19
    åĴĮåıijå±ķ
    0.19
    Activations Density 0.005%

    No Known Activations