© 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. 54391
    Prev
    Next
    INDEX
    Explanations

    starting or ending with punctuation

    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
     Laf
    -0.11
    aval
    -0.10
     blank
    -0.09
    ophone
    -0.09
    wand
    -0.09
     Composite
    -0.08
    //----------------------------------------------------------------------------↵
    -0.08
    uby
    -0.08
    speech
    -0.08
    aney
    -0.08
    POSITIVE LOGITS
     hedge
    0.11
     shaving
    0.08
     Shine
    0.08
     headlights
    0.08
     modes
    0.08
    ìł
    0.08
    .vm
    0.08
    jas
    0.08
    iam
    0.08
    mp
    0.08
    Activations Density 0.005%

    No Known Activations