© 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. 57841
    Prev
    Next
    INDEX
    Explanations

    copyright author emails

    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
    ngr
    -0.09
    pler
    -0.09
    uvre
    -0.08
    '*
    -0.08
    ű
    -0.08
    _Ptr
    -0.08
    '
    -0.08
     dumps
    -0.08
     Claus
    -0.08
     Kirk
    -0.08
    POSITIVE LOGITS
     allerg
    0.08
    ouch
    0.07
    ast
    0.07
    ainter
    0.07
    blogs
    0.07
     cong
    0.07
    /all
    0.07
    tx
    0.07
    _vi
    0.07
     ABI
    0.07
    Activations Density 0.054%

    No Known Activations