© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    damage

    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
    istan
    -0.09
    ical
    -0.09
    pir
    -0.09
     excess
    -0.09
    oses
    -0.09
    iej
    -0.09
    kh
    -0.09
    sp
    -0.09
    tv
    -0.09
    ists
    -0.09
    POSITIVE LOGITS
    able
    0.09
     kata
    0.09
     goods
    0.08
     perc
    0.08
    hoot
    0.08
    KT
    0.07
     sensitive
    0.07
    (effect
    0.07
    urm
    0.07
    hower
    0.07
    Activations Density 0.050%

    No Known Activations