© 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. 3120
    Prev
    Next
    INDEX
    Explanations

    saying that

    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
    /MIT
    -0.09
     Bout
    -0.08
    erne
    -0.08
    evin
    -0.08
     Zuk
    -0.08
     Sequential
    -0.08
    horn
    -0.07
    ldr
    -0.07
     thr
    -0.07
     discussing
    -0.07
    POSITIVE LOGITS
    agan
    0.09
     unrestricted
    0.09
    Latest
    0.09
     announce
    0.09
     Humb
    0.08
    otr
    0.08
     Express
    0.08
    mention
    0.08
     caution
    0.08
     say
    0.08
    Activations Density 0.277%

    No Known Activations