© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 242
    Prev
    Next
    INDEX
    Explanations

    $Id$, $Header$, $var$, $file$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $
    -0.10
     \(
    -0.08
    kest
    -0.07
    .nlm
    -0.07
     cul
    -0.07
    -turned
    -0.07
     $\
    -0.07
    pathname
    -0.07
    iff
    -0.07
    aan
    -0.07
    POSITIVE LOGITS
     Greens
    0.10
     Libert
    0.10
     Wand
    0.10
    aries
    0.09
    dk
    0.09
    ary
    0.09
     ToString
    0.09
    Serial
    0.09
    /Page
    0.09
    ARK
    0.09
    Activations Density 0.419%

    No Known Activations