© 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. 46897
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

    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
    agi
    -0.08
     Uk
    -0.07
    gid
    -0.07
    -priced
    -0.07
     att
    -0.07
     Divider
    -0.07
    roma
    -0.06
     evolving
    -0.06
    orian
    -0.06
    318
    -0.06
    POSITIVE LOGITS
     diameter
    0.22
     height
    0.20
     width
    0.20
     Diameter
    0.19
     length
    0.19
     size
    0.18
     dimensions
    0.17
     circumference
    0.17
     distance
    0.17
     diam
    0.17
    Activations Density 0.340%

    No Known Activations