© 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. 11925
    Prev
    Next
    INDEX
    Explanations

    DVDs and discs

    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
    åħ«åŃĹ
    -0.21
    æĥ³æ³ķ
    -0.21
    轿
    -0.20
    zug
    -0.20
    èľĩ
    -0.20
    -ag
    -0.20
     buildings
    -0.19
    微信群
    -0.19
    .alibaba
    -0.19
    èĩĨ
    -0.18
    POSITIVE LOGITS
    ç¢Ł
    0.34
    åĶ±çīĩ
    0.32
    åıijè¡Į
    0.29
    çĽĴ
    0.27
    çīĴ
    0.26
     discs
    0.25
     disk
    0.25
    鼶åĶ®
    0.25
    disk
    0.25
     диÑģк
    0.24
    Activations Density 0.072%

    No Known Activations