© 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. 54190
    Prev
    Next
    INDEX
    Explanations

    adverse effects or problems

    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
    unte
    -0.13
    /docs
    -0.11
    ylon
    -0.11
    902
    -0.11
    inel
    -0.11
     kw
    -0.10
    ouv
    -0.10
     Dillon
    -0.10
    enco
    -0.10
    UNCH
    -0.10
    POSITIVE LOGITS
    aim
    0.06
    orra
    0.06
     entail
    0.05
     haste
    0.05
     kin
    0.05
     mend
    0.05
     equal
    0.05
    imat
    0.05
     aimed
    0.05
     activates
    0.05
    Activations Density 0.084%

    No Known Activations