© 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. 3878
    Prev
    Next
    INDEX
    Explanations

    parse string to number

    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
     outweigh
    -0.09
    ł
    -0.08
    çĽ
    -0.08
    pts
    -0.08
    ohl
    -0.08
    ahrain
    -0.08
     PCs
    -0.08
     Pearce
    -0.08
    -ie
    -0.08
    ystick
    -0.08
    POSITIVE LOGITS
    alg
    0.10
    gro
    0.09
     scrim
    0.09
     somew
    0.09
     rap
    0.09
    rub
    0.08
     Musk
    0.08
     Jan
    0.08
    urances
    0.08
     gro
    0.08
    Activations Density 0.198%

    No Known Activations