© 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. 4146
    Prev
    Next
    INDEX
    Explanations

    place where

    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
    Ñĥм
    -0.10
     sheer
    -0.10
    stery
    -0.10
     FORCE
    -0.09
    inka
    -0.09
     Wishlist
    -0.09
    bring
    -0.09
     REGARD
    -0.09
    nah
    -0.09
    JECT
    -0.09
    POSITIVE LOGITS
     proceeded
    0.09
     `,
    0.09
    erton
    0.08
    yne
    0.07
    upon
    0.07
     Carp
    0.07
    359
    0.07
    ilton
    0.07
    smith
    0.07
     enjoyed
    0.06
    Activations Density 0.095%

    No Known Activations