© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2185
    Prev
    Next
    INDEX
    Explanations

    mixture of

    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
    icol
    -0.10
    tml
    -0.09
     connection
    -0.08
     plunge
    -0.08
     Bod
    -0.08
    irl
    -0.08
    /email
    -0.08
    .attachment
    -0.08
     def
    -0.08
     Alv
    -0.07
    POSITIVE LOGITS
     mix
    0.19
     mixture
    0.19
     Mix
    0.16
     MIX
    0.15
     mixed
    0.15
    Mix
    0.15
     mixes
    0.15
     ratio
    0.15
     mixing
    0.14
     Mixed
    0.14
    Activations Density 0.378%

    No Known Activations