© 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. 10986
    Prev
    Next
    INDEX
    Explanations

    India

    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
     ÐIJлекÑģан
    -0.24
     пÑĢиÑıÑĤн
    -0.21
    индивид
    -0.21
    èijĽ
    -0.20
    еÑģÑĤеÑģÑĤвенн
    -0.20
     ÐĶмиÑĤÑĢ
    -0.19
     Pt
    -0.19
    @dynamic
    -0.19
    VED
    -0.19
     wÅĽ
    -0.18
    POSITIVE LOGITS
    stretch
    0.21
    çĨ¨
    0.21
    æµĩæ°´
    0.19
    isko
    0.19
    ertz
    0.18
    å¼Ĥåij³
    0.18
    éĽªèĬ±
    0.18
    åħ¬åŃIJ
    0.18
    -cookie
    0.18
    æİĮæŁľ
    0.17
    Activations Density 0.399%

    No Known Activations