© 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. 3537
    Prev
    Next
    INDEX
    Explanations

    symbols and fragments

    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
    å§Ķç»Ħç»ĩéĥ¨
    -0.21
    ä¾ĺ
    -0.21
    ãİı
    -0.20
    å§Ķåī¯ä¹¦è®°
    -0.20
    \views
    -0.18
    ...
    -0.18
    çĩĥæĸĻ
    -0.18
    æĶĺ
    -0.17
    ationship
    -0.17
     getPrice
    -0.17
    POSITIVE LOGITS
    )||(
    0.25
    anje
    0.25
    ?";↵
    0.23
    :NO
    0.22
    ipsis
    0.21
    ĥ
    0.21
     Ãĸn
    0.21
    }->
    0.21
    çĽijåIJ¬é¡µéĿ¢
    0.21
     =>'
    0.20
    Activations Density 0.596%

    No Known Activations