© 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. 7199
    Prev
    Next
    INDEX
    Explanations

    gaps and alignment

    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
    ie
    -0.11
    angan
    -0.11
    rut
    -0.10
    chr
    -0.10
    worth
    -0.10
     slipping
    -0.10
    ieg
    -0.10
     tact
    -0.10
    scape
    -0.10
    :id
    -0.10
    POSITIVE LOGITS
    -mouth
    0.16
     gaping
    0.14
     open
    0.13
     hole
    0.13
     holes
    0.13
    -open
    0.13
     wounds
    0.13
    -hole
    0.12
    hole
    0.11
     gaps
    0.11
    Activations Density 0.002%

    No Known Activations