© 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. 1423
    Prev
    Next
    INDEX
    Explanations

    good + evaluation

    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
    ìŀĦ
    -0.09
     successfully
    -0.09
    hip
    -0.08
     homer
    -0.08
    idis
    -0.08
    focused
    -0.08
    -transfer
    -0.07
     lif
    -0.07
    ASE
    -0.07
    elijk
    -0.07
    POSITIVE LOGITS
    -quality
    0.21
    -looking
    0.17
     suited
    0.17
    -known
    0.17
    -fit
    0.16
    bye
    0.16
     behaved
    0.16
    (er
    0.16
     enough
    0.15
    seller
    0.14
    Activations Density 1.085%

    No Known Activations