© 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. 967
    Prev
    Next
    INDEX
    Explanations

    degree completion

    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
     Kle
    -0.08
     ...
    -0.07
    -plus
    -0.07
     rival
    -0.07
    -c
    -0.06
     Capitals
    -0.06
    Ķ
    -0.06
     put
    -0.06
    /c
    -0.06
     swear
    -0.06
    POSITIVE LOGITS
    //=
    0.10
    \Admin
    0.10
    /details
    0.10
    -Methods
    0.10
     nave
    0.10
    uchi
    0.10
    alg
    0.10
     noteworthy
    0.09
    (Cl
    0.09
    =>"
    0.09
    Activations Density 4.559%

    No Known Activations