© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 58884
    Prev
    Next
    INDEX
    Explanations

    tone of voice or arm

    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
    Negative Logits
    ly
    -0.13
     Flames
    -0.09
    LY
    -0.09
    -backed
    -0.09
    loquent
    -0.09
    liness
    -0.09
    (gl
    -0.08
    .NaN
    -0.08
    PHY
    -0.08
     Bast
    -0.08
    POSITIVE LOGITS
    arm
    0.10
    arms
    0.10
    uler
    0.10
    amb
    0.09
    umer
    0.09
    gard
    0.09
    udu
    0.09
    lessly
    0.09
    soever
    0.09
    eus
    0.08
    Activations Density 0.006%

    No Known Activations