© 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. 429
    Prev
    Next
    INDEX
    Explanations

    not only but also

    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
    ilestone
    -0.28
     unmist
    -0.28
    rvine
    -0.26
    apult
    -0.26
    cest
    -0.25
    ipop
    -0.25
    cestor
    -0.25
    loquent
    -0.25
    apons
    -0.24
     disappe
    -0.24
    POSITIVE LOGITS
    ä»İæł¹æľ¬
    0.32
    çĶ¨å¾®ä¿¡
    0.27
    éļıæŶéļı
    0.25
    Grün
    0.24
    æĮºå¥½
    0.23
    åıĸåĨ³
    0.23
    毫æĹłçĸij
    0.23
    è¶ĬæĿ¥
    0.23
    èĥ½çľĭåĩº
    0.23
    @include
    0.23
    Activations Density 6.427%

    No Known Activations