© 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. 13758
    Prev
    Next
    INDEX
    Explanations

    indigenous or tribal lands and peoples

    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
     heuristic
    -0.20
    åĪİ
    -0.19
    被æ·ĺæ±°
    -0.19
     Leban
    -0.19
    å½ķ
    -0.19
    åIJ¯åıij
    -0.18
    æijĦ
    -0.18
    æ°Ķè´¨
    -0.18
    packed
    -0.18
     strokes
    -0.18
    POSITIVE LOGITS
    åľŁåľ°
    0.27
    åĽ´
    0.22
    èĩªæ²»
    0.22
    æ¸ł
    0.21
     enclave
    0.21
    æĪIJç«ĭ以æĿ¥
    0.21
    .blank
    0.21
    urat
    0.20
    ç¦ıåĪ©
    0.20
     land
    0.20
    Activations Density 0.025%

    No Known Activations