© 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. 14788
    Prev
    Next
    INDEX
    Explanations

    tuberculosis

    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
    å¿ĥçĸ¼
    -0.25
    æѦè£ħ
    -0.21
    ches
    -0.21
    毽
    -0.21
    大æĸ¹
    -0.20
    éĽ¹
    -0.20
    ä¸ĢèĦļ
    -0.19
    occer
    -0.19
    å¹ħ
    -0.19
     robber
    -0.19
    POSITIVE LOGITS
    éļĶ离
    0.26
    æİ¢
    0.25
     isolation
    0.20
    æ£Ģçĸ«
    0.20
    iously
    0.20
    bv
    0.20
     quarantine
    0.19
    æī©æķ£
    0.19
    Č
    0.18
    krä
    0.18
    Activations Density 0.040%

    No Known Activations