© 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. 3626
    Prev
    Next
    INDEX
    Explanations

    post or create content

    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
     vac
    -0.07
    uga
    -0.07
     vest
    -0.07
    cop
    -0.06
     acqu
    -0.06
    anga
    -0.06
    SSL
    -0.06
     imitation
    -0.06
    agna
    -0.06
     virgin
    -0.06
    POSITIVE LOGITS
     CONTR
    0.12
     wards
    0.11
    uds
    0.11
     Ability
    0.10
    yer
    0.10
    eld
    0.10
     Weld
    0.10
    781
    0.10
     perks
    0.10
     Capability
    0.10
    Activations Density 0.264%

    No Known Activations