© 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. 13
    Prev
    Next
    INDEX
    Explanations

    authorities

    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
     anv
    -0.26
    Animating
    -0.25
     Hannity
    -0.23
    irlines
    -0.23
     QLD
    -0.22
    åħļå·¥å§Ķ
    -0.22
     RaisePropertyChanged
    -0.21
     porr
    -0.21
     councillor
    -0.21
    è®°èĢħåľ¨
    -0.21
    POSITIVE LOGITS
    å½ĵåľ°æĶ¿åºľ
    0.28
    "label
    0.27
     local
    0.27
    å½ĵåľ°
    0.26
     authorities
    0.24
    Synopsis
    0.24
     Kardash
    0.23
    åħ¶ä»ĸçݩ家
    0.23
     Aviv
    0.23
    éĥ¨åī¯
    0.23
    Activations Density 5.890%

    No Known Activations