© 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. 16750
    Prev
    Next
    INDEX
    Explanations

    authorities, talks, ologists

    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
    åŃĹåı·
    -0.21
    parm
    -0.20
    çģŃ亡
    -0.20
    omm
    -0.19
     Agency
    -0.19
     пÑĢедÑĥÑģмоÑĤÑĢ
    -0.18
    åľ¨åħ¶
    -0.18
    俱
    -0.18
    踮
    -0.18
    “She
    -0.17
    POSITIVE LOGITS
    Hom
    0.19
     Hom
    0.18
     writ
    0.18
    åł¡
    0.18
    asta
    0.17
    MR
    0.17
    çļĦå¿ĥçIJĨ
    0.17
    çīĮ
    0.17
    ully
    0.17
    URRE
    0.17
    Activations Density 0.228%

    No Known Activations