© 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. 148
    Prev
    Next
    INDEX
    Explanations

    Labels and identifiers

    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
    emetery
    -0.23
     Fauc
    -0.23
    loquent
    -0.22
    abcdefghijklmnop
    -0.20
     novitÃł
    -0.20
    å¤Ļ
    -0.20
     yat
    -0.20
     ActionTypes
    -0.20
    opportunitÃł
    -0.20
    -Compatible
    -0.19
    POSITIVE LOGITS
     jihadists
    0.23
    ppard
    0.23
    redient
    0.20
    æľīè¿ĩ
    0.18
    åģ¥åħ¨
    0.18
    _ta
    0.18
    çļ®
    0.18
    åºĸ
    0.18
    çķĪ
    0.18
    é£ķ
    0.18
    Activations Density 0.001%

    No Known Activations