© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3660
    Prev
    Next
    INDEX
    Explanations

    cities and places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
    .offsetHeight
    -0.23
    :".$
    -0.23
    <=(
    -0.22
    żeli
    -0.21
    .bumptech
    -0.21
    å¹´ä¹ĭä¹ħ
    -0.20
    datable
    -0.20
    å½ĵä¹ĭ
    -0.19
    ãģŀ
    -0.19
     ++)↵
    -0.19
    POSITIVE LOGITS
    建档ç«ĭ
    0.24
     citiz
    0.23
    对åħ¶çľŁå®ŀ
    0.23
    Cumh
    0.20
    CEE
    0.20
     décid
    0.20
    ampie
    0.20
     vegas
    0.19
    åıĪ好åıĪå¿«
    0.19
     frankfurt
    0.19
    Activations Density 0.934%

    No Known Activations