© 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. 8359
    Prev
    Next
    INDEX
    Explanations

    body parts and posture

    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
    "↵↵↵↵
    -0.10
     punct
    -0.10
     twee
    -0.10
     Bracket
    -0.10
    toi
    -0.10
     Blind
    -0.09
    itu
    -0.09
     Interface
    -0.09
    abr
    -0.09
     Giant
    -0.09
    POSITIVE LOGITS
     relaxed
    0.10
     consciously
    0.08
     forward
    0.08
     sank
    0.08
     compens
    0.08
     pigeon
    0.08
     contracted
    0.08
     Belmont
    0.07
     exagger
    0.07
     chest
    0.07
    Activations Density 0.116%

    No Known Activations