© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54324
    Prev
    Next
    INDEX
    Explanations

    Definitely not

    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
     lesser
    -0.08
    ко
    -0.08
     deny
    -0.08
    ropp
    -0.07
     prominent
    -0.07
    _URI
    -0.07
     eminent
    -0.07
    (global
    -0.07
    Href
    -0.07
     prominently
    -0.07
    POSITIVE LOGITS
     deb
    0.11
     bypass
    0.10
    apl
    0.10
     Mixed
    0.10
    bourg
    0.09
     unsur
    0.09
    aktion
    0.09
     jumps
    0.08
     extended
    0.08
     misd
    0.08
    Activations Density 0.051%

    No Known Activations