© 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. 54416
    Prev
    Next
    INDEX
    Explanations

    lengths and distances

    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
     Tear
    -0.07
    opr
    -0.07
     departure
    -0.07
    burger
    -0.07
    oce
    -0.07
     filter
    -0.07
     tear
    -0.07
    LAS
    -0.07
    arty
    -0.07
     narrowed
    -0.07
    POSITIVE LOGITS
     distance
    0.12
    uda
    0.11
    -length
    0.11
     length
    0.11
    trs
    0.11
    distance
    0.11
     Distance
    0.11
    ,length
    0.10
     distances
    0.10
    .distance
    0.10
    Activations Density 0.043%

    No Known Activations