© 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. 10961
    Prev
    Next
    INDEX
    Explanations

    US states, cities, and districts

    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
    toolbox
    -0.23
    çĶµç¼Ĩ
    -0.22
    éªĬ
    -0.21
    lags
    -0.20
    累累
    -0.20
     Assad
    -0.19
    urb
    -0.19
    ikh
    -0.19
    BLUE
    -0.19
    las
    -0.19
    POSITIVE LOGITS
    æ¼³
    0.25
     Berkshire
    0.24
    .gov
    0.23
    æŁ´
    0.22
    ç»ıè´¹
    0.21
    æĬ±
    0.21
    çĦĻ
    0.19
    æłİ
    0.19
    èIJģ
    0.19
     bras
    0.19
    Activations Density 0.758%

    No Known Activations