© 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. 4006
    Prev
    Next
    INDEX
    Explanations

    how to do something

    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
    usan
    -0.10
    acin
    -0.09
     Ellis
    -0.09
     Lud
    -0.09
     existed
    -0.08
    .CR
    -0.08
    -l
    -0.07
    mission
    -0.07
    english
    -0.07
    isle
    -0.07
    POSITIVE LOGITS
    ìłľ
    0.10
     Granite
    0.09
     vel
    0.09
    aro
    0.09
     Gray
    0.09
     prob
    0.08
     sph
    0.08
    nt
    0.08
    arin
    0.08
     invent
    0.08
    Activations Density 0.132%

    No Known Activations