© 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. 46155
    Prev
    Next
    INDEX
    Explanations

    self.canvas drawing

    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
     buc
    -0.27
    ">ÃĹ</
    -0.25
     Toro
    -0.24
    į°ìĿ´
    -0.23
     darm
    -0.23
    å®ŀäºĭæ±Ĥ
    -0.22
    å°±ç»Ļ大家
    -0.22
    PropTypes
    -0.22
    nze
    -0.21
    lyph
    -0.21
    POSITIVE LOGITS
     accept
    0.20
    CAPE
    0.20
    æ²ģ
    0.19
    rez
    0.19
    .shiro
    0.18
    ofstream
    0.18
     replacing
    0.18
    (low
    0.18
     acceptance
    0.18
     Malays
    0.18
    Activations Density 0.001%

    No Known Activations