© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 23
    Prev
    Next
    INDEX
    Explanations

    isolation

    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
    Negative Logits
    æĿ¥çľĭçľĭåIJ§
    -0.29
    æĿ¨å¹Ĥ
    -0.23
    èĮĥåĨ°åĨ°
    -0.22
    **
    -0.21
    åıijå±ķæł¼å±Ģ
    -0.20
    æĪ¿ä¸ľ
    -0.20
    .P
    -0.20
    æı¶
    -0.20
    å§Ķå®£ä¼łéĥ¨
    -0.20
    ç°Į
    -0.19
    POSITIVE LOGITS
    (Have
    0.35
    ');↵↵↵↵
    0.34
    'icon
    0.33
    ;base
    0.31
    IFn
    0.31
    ;o
    0.31
    hế
    0.31
    -Compatible
    0.31
    peare
    0.30
    ;;;;;;;;
    0.29
    Activations Density 8.469%

    No Known Activations