© 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. 4214
    Prev
    Next
    INDEX
    Explanations

    -ose, -ine, -atic, -eric

    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
    eken
    -0.10
     Vic
    -0.10
    APPER
    -0.10
     autoplay
    -0.09
    _sku
    -0.09
     Seks
    -0.09
    adir
    -0.08
    BU
    -0.08
     Gamb
    -0.08
    eler
    -0.08
    POSITIVE LOGITS
     versions
    0.10
    çīĪ
    0.08
     instances
    0.08
    /ex
    0.08
     naked
    0.07
    level
    0.07
    exo
    0.07
     Trace
    0.07
    up
    0.07
    /f
    0.07
    Activations Density 0.800%

    No Known Activations