© 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-CHAT-65K
    7. 46506
    Prev
    Next
    INDEX
    Explanations

    places

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ıåľ¨
    -0.25
     ElementRef
    -0.22
    çĸı
    -0.21
    благо
    -0.21
    วà¸ĩ
    -0.21
    çĶŁæ´»åľ¨
    -0.21
    '=>"
    -0.20
    aterno
    -0.20
    FetchRequest
    -0.19
    esda
    -0.18
    POSITIVE LOGITS
    åľºæīĢ
    0.32
     staging
    0.29
     meeting
    0.27
    交æĺĵå¹³åı°
    0.25
     platform
    0.24
    ä¸ĵçĶ¨
    0.24
     destination
    0.23
     platforms
    0.23
    å¹³åı°
    0.23
    åľ°çĤ¹
    0.23
    Activations Density 0.233%

    No Known Activations