© 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. 3535
    Prev
    Next
    INDEX
    Explanations

    professional practice guidelines

    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
     appDelegate
    -0.23
    CLUDING
    -0.21
     Webseite
    -0.21
     isAuthenticated
    -0.20
    -fin
    -0.20
    éĥ¨åī¯
    -0.20
    s
    -0.20
    /int
    -0.19
     ActionTypes
    -0.19
    ÑģÑĤÑĢÑĥкÑĤоÑĢ
    -0.18
    POSITIVE LOGITS
    .']
    0.31
    stdarg
    0.28
    gnore
    0.28
    Ỹ
    0.27
    estruction
    0.27
    ä¹łè¿ij
    0.27
    ->[
    0.26
    __:
    0.26
    )\<
    0.25
     ×Ķ×ķ×ĵ
    0.25
    Activations Density 0.062%

    No Known Activations