© 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. 3024
    Prev
    Next
    INDEX
    Explanations

    influence legacy

    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
    âĦī
    -0.25
    婪
    -0.24
     currently
    -0.24
    ,");↵
    -0.23
    ä¸Ĭ次
    -0.23
    ".↵↵↵↵
    -0.21
    åı¤èĢģçļĦ
    -0.21
    åı¤èĢģ
    -0.21
    _ISR
    -0.20
    currently
    -0.20
    POSITIVE LOGITS
    ä¸ĢçĶŁ
    0.30
     influence
    0.27
    ç»ĪçĶŁ
    0.24
    æĻļå¹´
    0.24
    æ®ģ
    0.23
    å½±åĵį
    0.23
    çļĦå½±åĵį
    0.23
     legacy
    0.23
     influential
    0.22
    åIJİæľŁ
    0.22
    Activations Density 0.850%

    No Known Activations