© 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. 3315
    Prev
    Next
    INDEX
    Explanations

    events or time

    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
     nomine
    -0.27
    anmar
    -0.26
    _VC
    -0.22
    icipation
    -0.21
    essages
    -0.20
    exampleInputEmail
    -0.20
    irlines
    -0.20
     blowjob
    -0.19
    vably
    -0.19
     Venue
    -0.19
    POSITIVE LOGITS
     annual
    0.26
    çķ¸
    0.24
    èĤ¡ä¸ľå¤§ä¼ļ
    0.22
     subsequent
    0.21
     fall
    0.21
    adesh
    0.21
    ç§ĭåŃ£
    0.21
    école
    0.20
     ******************************************************************************↵
    0.20
     summer
    0.20
    Activations Density 0.831%

    No Known Activations