© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3700
    Prev
    Next
    INDEX
    Explanations

    code fragments

    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
    ={['
    -0.23
    èĤ¸
    -0.19
    acier
    -0.19
     Prosecutor
    -0.18
    Locator
    -0.18
    GetPosition
    -0.18
    âĺ°
    -0.18
    å¿«
    -0.17
    IBUT
    -0.17
    FormControl
    -0.17
    POSITIVE LOGITS
    .ToShort
    0.23
    .ManyToMany
    0.22
    =$("#
    0.20
    ä¸ªåĽ½å®¶
    0.20
     Politico
    0.20
    ERGY
    0.19
    .Abstractions
    0.19
     ($.
    0.19
     Holidays
    0.19
     ');↵↵
    0.19
    Activations Density 0.029%

    No Known Activations