© 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. 4252
    Prev
    Next
    INDEX
    Explanations

    message or topic titles

    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
    ly
    -0.12
    itor
    -0.09
    ish
    -0.09
    rn
    -0.09
    azon
    -0.09
    erez
    -0.09
    /misc
    -0.09
    /dom
    -0.08
    yas
    -0.08
    Mail
    -0.08
    POSITIVE LOGITS
     boards
    0.13
    boards
    0.12
     Boards
    0.12
    Erreur
    0.11
    .SEVER
    0.11
     board
    0.11
    /rfc
    0.10
    nds
    0.10
     Passing
    0.09
    еÑģÑĤв
    0.09
    Activations Density 0.106%

    No Known Activations