© 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. 57273
    Prev
    Next
    INDEX
    Explanations

    section tags or chapter tags

    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
    led
    -0.08
    ücken
    -0.07
    ioni
    -0.07
    eng
    -0.07
     Museum
    -0.07
    rupt
    -0.07
    urgeon
    -0.07
    ör
    -0.06
    ös
    -0.06
    ject
    -0.06
    POSITIVE LOGITS
     Tu
    0.11
    fall
    0.10
    ativa
    0.10
    tie
    0.10
     woo
    0.10
     Ross
    0.10
    uctor
    0.09
     killer
    0.09
    Robin
    0.09
    ?t
    0.09
    Activations Density 0.004%

    No Known Activations