© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111843
    Prev
    Next
    INDEX
    Explanations

    sentence length in years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rebel
    -0.11
     disobed
    -0.11
     curses
    -0.10
     CB
    -0.09
     rebels
    -0.09
     rebellion
    -0.09
     Electron
    -0.09
    CB
    -0.09
     Meer
    -0.09
     Bru
    -0.09
    POSITIVE LOGITS
     prison
    0.24
     sentence
    0.22
     sentencing
    0.21
     jail
    0.21
     sentenced
    0.20
     incarceration
    0.20
     imprisonment
    0.19
     sentences
    0.19
     prisons
    0.19
     incarcerated
    0.18
    Activations Density 0.132%

    No Known Activations