© 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. 2142
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    IFn
    -0.21
    xffff
    -0.20
    åıĺäºĨ
    -0.20
    inheritdoc
    -0.20
    ={()=>
    -0.19
    éĻ¢åī¯éĻ¢éķ¿
    -0.19
     defenseman
    -0.18
    èīı
    -0.18
    xFFFF
    -0.18
    9
    -0.18
    POSITIVE LOGITS
     Åģa
    0.23
    FOX
    0.22
    bben
    0.22
    -END
    0.22
     Oczy
    0.22
    "label
    0.21
    <context
    0.20
    )))));č↵
    0.20
    .AdapterView
    0.20
    "<?
    0.19
    Activations Density 0.002%

    No Known Activations