© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4921
    Prev
    Next
    INDEX
    Explanations

    considering briefs and record

    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
    Negative Logits
    ll
    -0.08
     straw
    -0.08
    alic
    -0.07
     hypo
    -0.07
    iable
    -0.07
     rectangular
    -0.07
     later
    -0.07
    uy
    -0.07
     definit
    -0.07
    Bold
    -0.07
    POSITIVE LOGITS
    INCLUDING
    0.11
     available
    0.11
     everything
    0.10
    agar
    0.10
    unter
    0.10
    igo
    0.10
     consideration
    0.10
    hart
    0.10
     tot
    0.09
     considerations
    0.09
    Activations Density 0.044%

    No Known Activations