© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 860
    Prev
    Next
    INDEX
    Explanations

    cause or reason

    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
    |array
    -0.31
    -Semit
    -0.28
    thinkable
    -0.28
     libertin
    -0.28
    (Collision
    -0.27
    (Collider
    -0.26
     fkk
    -0.26
    .ibatis
    -0.25
    /*↵
    -0.24
    linky
    -0.24
    POSITIVE LOGITS
    äºİ
    0.24
    äºİä¸Ģä½ĵ
    0.21
     of
    0.21
    æľĭ
    0.20
    .PrintWriter
    0.20
    }elseif
    0.20
    .removeListener
    0.19
    æĸ¼
    0.19
    FY
    0.19
    :checked
    0.19
    Activations Density 4.863%

    No Known Activations