© 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. 55403
    Prev
    Next
    INDEX
    Explanations

    influence and impact

    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
    mb
    -0.08
     MV
    -0.08
     bulk
    -0.08
     complementary
    -0.07
     JV
    -0.07
     supplement
    -0.07
    èģĶ
    -0.07
     mans
    -0.07
    Supported
    -0.07
     sur
    -0.07
    POSITIVE LOGITS
     Influence
    0.17
     influencing
    0.15
     influence
    0.14
     successor
    0.14
    spawn
    0.14
     descendant
    0.12
     influences
    0.12
     influential
    0.12
     successors
    0.12
     descendants
    0.12
    Activations Density 0.067%

    No Known Activations