© 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. 54999
    Prev
    Next
    INDEX
    Explanations

    invalid syntax, date, type, token, email, handler

    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
    rama
    -0.10
    å¡
    -0.10
    INGS
    -0.10
     defensively
    -0.09
    ionic
    -0.09
    ÑħÑĢан
    -0.09
    ills
    -0.09
    ives
    -0.09
    leo
    -0.09
    ring
    -0.08
    POSITIVE LOGITS
     dims
    0.10
    eer
    0.09
    ise
    0.09
    ing
    0.09
    ADE
    0.09
    ation
    0.08
    erne
    0.08
    esan
    0.08
     HEX
    0.08
    o
    0.08
    Activations Density 0.004%

    No Known Activations