© 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. 12108
    Prev
    Next
    INDEX
    Explanations

    urban development and transit

    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
    ç§ijåĪĽæĿ¿
    -0.19
    bote
    -0.19
    _deinit
    -0.19
    çĽijçĿ£æ£ĢæŁ¥
    -0.19
    _subject
    -0.19
    .gpu
    -0.18
     диÑģк
    -0.18
    _MACHINE
    -0.18
    ammers
    -0.18
    .rl
    -0.18
    POSITIVE LOGITS
    æijĶ
    0.24
    èµ°å¾Ĺ
    0.23
     town
    0.23
     terr
    0.21
    ç»ĵæŀĦ
    0.20
     towns
    0.20
     spraw
    0.20
     retrofit
    0.19
     Urb
    0.19
    åħ¬åħ±äº¤éĢļ
    0.19
    Activations Density 0.017%

    No Known Activations