© 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. 3805
    Prev
    Next
    INDEX
    Explanations

    wave computing, gear, guides, front

    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
     unb
    -0.08
    ified
    -0.08
    agram
    -0.08
     hole
    -0.08
    luck
    -0.07
    ANT
    -0.07
    ahlen
    -0.07
    s
    -0.07
     versch
    -0.07
    lando
    -0.07
    POSITIVE LOGITS
    front
    0.13
     goodbye
    0.12
    forms
    0.12
    guide
    0.12
    -front
    0.11
    let
    0.10
     fronts
    0.10
    lets
    0.10
    adero
    0.10
    pell
    0.09
    Activations Density 0.102%

    No Known Activations