© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57165
    Prev
    Next
    INDEX
    Explanations

    parentheses with numbers inside

    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
    istr
    -0.09
    portion
    -0.09
    awa
    -0.09
    aje
    -0.09
    .encode
    -0.08
    ucc
    -0.08
    .Raw
    -0.08
     underside
    -0.07
    约
    -0.07
     unde
    -0.07
    POSITIVE LOGITS
    joining
    0.09
    etro
    0.09
     Rip
    0.09
    owered
    0.08
     Lewis
    0.08
    bak
    0.08
     ripple
    0.08
    ts
    0.08
     Plug
    0.08
     Chall
    0.08
    Activations Density 0.005%

    No Known Activations