© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29513
    Prev
    Next
    INDEX
    Explanations

    inside and internal

    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
    jon
    -0.10
    letics
    -0.10
     ambit
    -0.09
    ffield
    -0.09
    nym
    -0.09
    opia
    -0.09
    yr
    -0.09
    tat
    -0.09
    atics
    -0.08
    inia
    -0.08
    POSITIVE LOGITS
     internally
    0.61
     internal
    0.58
     inward
    0.53
     Internal
    0.48
     inner
    0.48
     internals
    0.47
    internal
    0.47
     inside
    0.45
     interior
    0.45
    åĨħ
    0.44
    Activations Density 0.175%

    No Known Activations