© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6213
    Prev
    Next
    INDEX
    Explanations

    pens and ink

    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
     tile
    -0.10
     Wich
    -0.10
     pan
    -0.10
     Fro
    -0.10
     tiles
    -0.10
     traps
    -0.09
     rever
    -0.09
     pedals
    -0.09
     plates
    -0.09
     plate
    -0.09
    POSITIVE LOGITS
     pen
    0.26
     Pens
    0.25
     pens
    0.25
     ink
    0.22
     Ink
    0.20
     Scri
    0.20
     nib
    0.20
     Pen
    0.19
     scri
    0.18
    pen
    0.17
    Activations Density 0.228%

    No Known Activations