© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 367
    Prev
    Next
    INDEX
    Explanations

    relating to

    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
     nostalg
    -0.28
    _grupo
    -0.26
    vertime
    -0.26
     burge
    -0.25
     misd
    -0.24
    _registro
    -0.24
    FormattedMessage
    -0.24
    FirstChild
    -0.23
    ãģ«åħ¥ãģ£ãģŁ
    -0.23
     inkl
    -0.23
    POSITIVE LOGITS
     to
    0.41
    åĪ°
    0.37
    åĻĮ
    0.30
    _to
    0.30
    æĬī
    0.27
    âĩĶ
    0.27
    âĨ©
    0.26
    ï¸
    0.26
    sto
    0.26
    	to
    0.26
    Activations Density 6.604%

    No Known Activations