© 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. 2093
    Prev
    Next
    INDEX
    Explanations

    actions

    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
     imm
    -0.08
     Estimate
    -0.08
    bak
    -0.08
     ambush
    -0.08
     unexpected
    -0.08
     full
    -0.07
    Frozen
    -0.07
    _physical
    -0.07
    unsafe
    -0.07
    Cars
    -0.07
    POSITIVE LOGITS
     industri
    0.11
    rium
    0.09
    obox
    0.09
    /change
    0.09
    izzle
    0.09
     meticulously
    0.09
     neatly
    0.09
     clums
    0.09
    leccion
    0.09
     Pall
    0.09
    Activations Density 0.099%

    No Known Activations