© 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. 28040
    Prev
    Next
    INDEX
    Explanations

    an followed by a word starting with a vowel

    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
     freely
    -0.09
    period
    -0.08
     visually
    -0.08
     comparable
    -0.08
    !!!!
    -0.08
    uster
    -0.08
     privately
    -0.08
     downstream
    -0.08
    mination
    -0.07
    foot
    -0.07
    POSITIVE LOGITS
    ther
    0.21
     awful
    0.20
    ointed
    0.19
    vil
    0.19
    agrams
    0.18
     assortment
    0.18
     envelope
    0.18
     attempt
    0.18
    archy
    0.18
     occasional
    0.18
    Activations Density 0.804%

    No Known Activations