© 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. 16821
    Prev
    Next
    INDEX
    Explanations

    sides, surfaces, and faces

    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
    inspace
    -0.25
    念
    -0.23
    ennon
    -0.21
    åľ°éģĵ
    -0.20
    æĬī
    -0.19
    rick
    -0.19
    ziel
    -0.19
    éĵĦ
    -0.19
    æķ¬çķı
    -0.19
    obox
    -0.18
    POSITIVE LOGITS
     faces
    0.35
    ä¸ĢéĿ¢
    0.33
     facing
    0.33
     sides
    0.33
    ä¸Ģ侧
    0.31
     face
    0.31
    faces
    0.31
     surfaces
    0.30
    èĥĮéĿ¢
    0.30
    side
    0.30
    Activations Density 0.170%

    No Known Activations