© 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. 2601
    Prev
    Next
    INDEX
    Explanations

    remote or virtual

    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
    æĿ¨æ¬¢
    -0.21
    rarian
    -0.20
    itere
    -0.20
    å§ĭ建
    -0.20
    ummings
    -0.19
    æī«é»ij
    -0.19
    >{"
    -0.19
    ocity
    -0.19
    游æĪıæĵįä½ľ
    -0.19
     Noticed
    -0.19
    POSITIVE LOGITS
     remote
    0.44
    è¿ľç¨ĭ
    0.43
    remote
    0.38
    èĻļæĭŁ
    0.38
    Remote
    0.36
     Remote
    0.36
     virtual
    0.36
     online
    0.35
    è¿ľæĸ¹
    0.33
    virtual
    0.32
    Activations Density 0.910%

    No Known Activations