© 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. 2088
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     gameTime
    -0.21
    ä¹Įåħĭ
    -0.20
     jihadist
    -0.19
    :disable
    -0.18
    ".$_
    -0.18
     Breitbart
    -0.18
    setSize
    -0.18
    åħ¨èµĦåŃIJ
    -0.18
    İĺìĿ´
    -0.18
    LOBAL
    -0.18
    POSITIVE LOGITS
    hế
    0.22
    adoo
    0.19
    )application
    0.19
    edium
    0.19
    aits
    0.18
    		č↵		č↵
    0.18
     cripp
    0.18
    oren
    0.18
    _HOUR
    0.18
    ç¯Ħ
    0.18
    Activations Density 0.921%

    No Known Activations