© 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. 1581
    Prev
    Next
    INDEX
    Explanations

    spatial directions and orientation

    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
    fp
    -0.11
     Humph
    -0.10
    /errors
    -0.10
    FP
    -0.10
    estar
    -0.10
    >j
    -0.10
    /li
    -0.10
     Branch
    -0.09
     AMA
    -0.09
     Jump
    -0.09
    POSITIVE LOGITS
     direction
    0.17
     directions
    0.14
     axis
    0.14
    -axis
    0.13
    -direction
    0.12
     orientation
    0.11
     projection
    0.11
     axes
    0.11
     Direction
    0.10
     Projection
    0.10
    Activations Density 1.285%

    No Known Activations