© 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. 3229
    Prev
    Next
    INDEX
    Explanations

    code initialization or structure

    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
     jeep
    -0.10
     elective
    -0.10
     SOS
    -0.09
     TER
    -0.09
     Penal
    -0.09
     Athena
    -0.09
    .gc
    -0.09
     ==============================================================
    -0.09
    meno
    -0.09
    rone
    -0.09
    POSITIVE LOGITS
    cond
    0.09
    <|fim_middle|>
    0.08
    -cond
    0.08
     proceeding
    0.08
     nerv
    0.08
     remotely
    0.07
     pulver
    0.07
     cond
    0.07
     conveyed
    0.07
    .Then
    0.07
    Activations Density 0.040%

    No Known Activations