© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17601
    Prev
    Next
    INDEX
    Explanations

    "Where" questions about location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    ÑģÑĤаÑĢ
    -0.06
     جداÙĭ
    -0.06
    家常
    -0.06
    åģ¥
    -0.06
    наÑĤ
    -0.05
     vielä
    -0.05
    èħ±
    -0.05
    remark
    -0.05
    æij©æł¹
    -0.05
    天åı°
    -0.05
    POSITIVE LOGITS
    alles
    0.06
    ÙĪدÙĬ
    0.05
    enje
    0.05
    她çļĦæīĭ
    0.05
     |[
    0.05
    Mono
    0.05
    вое
    0.05
    /or
    0.05
    odob
    0.05
    burgo
    0.05
    Activations Density 0.006%

    No Known Activations