© 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. 56100
    Prev
    Next
    INDEX
    Explanations

    URL fragment identifiers

    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
    åıĭ
    -0.09
     Hurt
    -0.09
    variably
    -0.09
     suit
    -0.09
     paran
    -0.08
    itter
    -0.08
    pole
    -0.08
     pole
    -0.08
    mr
    -0.08
    ÙIJ
    -0.08
    POSITIVE LOGITS
    /off
    0.09
     Armstrong
    0.08
    cher
    0.08
    .exec
    0.08
     vd
    0.08
     consec
    0.08
    -article
    0.08
     hum
    0.08
    ions
    0.08
    ef
    0.08
    Activations Density 0.002%

    No Known Activations