© 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. 3564
    Prev
    Next
    INDEX
    Explanations

    biological processes

    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
    çĭłæĬĵ
    -0.22
    setWidth
    -0.21
     actionTypes
    -0.20
     دÙĤ
    -0.20
    +"<
    -0.19
    ä¾Ľ
    -0.19
    èĥ
    -0.19
    __);
    -0.19
    ìĵ¸
    -0.19
    alse
    -0.18
    POSITIVE LOGITS
    ->{'
    0.24
    PictureBox
    0.22
    GameManager
    0.20
    çļĦç¬ij容
    0.20
    "crypto
    0.20
    ActionTypes
    0.19
    iske
    0.19
    )null
    0.19
    ::_
    0.19
    +)\
    0.18
    Activations Density 0.550%

    No Known Activations