© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    things are being done

    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
    /Dk
    -0.27
     )↵↵↵↵↵↵↵↵
    -0.24
    æį¢åı¥è¯Ŀ
    -0.23
     wonders
    -0.21
     masturbating
    -0.21
    å§Ķç»Ħç»ĩ
    -0.21
    éĥ¨åī¯
    -0.20
    æľīä¸Ģ
    -0.20
    对åħ¶çľŁå®ŀ
    -0.20
    ernote
    -0.19
    POSITIVE LOGITS
    elor
    0.22
    InChildren
    0.21
    oled
    0.21
    rades
    0.21
    aped
    0.21
    OutOfRangeException
    0.20
    带åĪ°
    0.20
    ç§ģä¸ĭ
    0.20
    çĶ¨æĿ¥
    0.20
    (DIR
    0.19
    Activations Density 1.337%

    No Known Activations