© 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. 1784
    Prev
    Next
    INDEX
    Explanations

    fight

    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
     ámb
    -0.29
    微软éĽħé»ij
    -0.27
    æįĮ
    -0.27
    ullets
    -0.25
    绺
    -0.24
    åĹ«
    -0.24
     Relatives
    -0.24
     Parenthood
    -0.24
     Fireplace
    -0.24
    èĭ¦ç¬ij
    -0.24
    POSITIVE LOGITS
    (Have
    0.34
    NavLink
    0.28
    FontAwesomeIcon
    0.27
    scripción
    0.26
    FormGroup
    0.25
    sembling
    0.24
    imageName
    0.24
    /testify
    0.24
    RouterModule
    0.24
    FormsModule
    0.23
    Activations Density 8.619%

    No Known Activations