© 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. 2093
    Prev
    Next
    INDEX
    Explanations

    prior art

    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
     ntohs
    -0.26
    _APB
    -0.22
     bietet
    -0.21
    个çĻ¾åĪĨ
    -0.20
     Decompiled
    -0.20
     htons
    -0.20
     RedirectTo
    -0.20
    nofollow
    -0.19
    	AND
    -0.19
    æİĴè¡Į
    -0.19
    POSITIVE LOGITS
    -wsj
    0.23
    .sz
    0.21
    §è¡Į
    0.20
    TargetException
    0.20
    CHASE
    0.20
    onomy
    0.20
    ?option
    0.20
    icaid
    0.20
    ;left
    0.19
    omore
    0.19
    Activations Density 0.001%

    No Known Activations