© 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. 2186
    Prev
    Next
    INDEX
    Explanations

    after semicolon or `use`

    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
     ob
    -0.08
    irim
    -0.07
    te
    -0.07
    erb
    -0.07
    uchen
    -0.06
    via
    -0.06
    Ob
    -0.06
     Sommer
    -0.06
    âĢİ
    -0.06
    rms
    -0.06
    POSITIVE LOGITS
    linky
    0.12
    >//
    0.10
    apat
    0.10
     swe
    0.10
    spinner
    0.10
    vro
    0.09
    _GU
    0.09
    onth
    0.09
    apg
    0.09
    /assert
    0.09
    Activations Density 0.286%

    No Known Activations