© 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. 1526
    Prev
    Next
    INDEX
    Explanations

    }

    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
    ä»İ容
    -0.22
     nues
    -0.21
    ly
    -0.19
    .assertNull
    -0.19
    åĦ¿
    -0.19
    \Carbon
    -0.18
    oplayer
    -0.18
    wayne
    -0.18
    owy
    -0.18
    /***************************************************************************↵
    -0.18
    POSITIVE LOGITS
    ">//
    0.24
    交代
    0.23
    æį¢åı¥è¯Ŀ
    0.23
    ".$_
    0.21
    :hidden
    0.20
    *>*
    0.20
    .="
    0.20
    .='
    0.20
    )":
    0.20
     démarch
    0.20
    Activations Density 0.283%

    No Known Activations