© 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. 16213
    Prev
    Next
    INDEX
    Explanations

    protests, riots, and public demonstrations

    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
    ä½łéľĢè¦ģ
    -0.23
    ç»ĨåĪĨ
    -0.19
    çķ¦
    -0.19
    çĸijéļ¾
    -0.19
    对åŃ©åŃIJ
    -0.19
    éĻ·éĺ±
    -0.18
    好å¥ĩå¿ĥ
    -0.18
    /editor
    -0.18
    ÑĤÑıж
    -0.18
    åī¿
    -0.17
    POSITIVE LOGITS
     naked
    0.21
    éĻĦè¿ijçļĦ
    0.21
    PropertyParams
    0.20
    æĬĹè®®
    0.20
    天é¹ħ
    0.20
    illos
    0.19
    .reject
    0.19
    åij¨åĽ´
    0.19
     symbolic
    0.18
    gMaps
    0.18
    Activations Density 0.031%

    No Known Activations