© 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. 29398
    Prev
    Next
    INDEX
    Explanations

    pen and related words

    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
     satur
    -0.09
    lian
    -0.09
    faction
    -0.09
    ringe
    -0.08
    leur
    -0.08
     Cypress
    -0.08
    ync
    -0.08
    vie
    -0.08
    isers
    -0.08
    -Methods
    -0.08
    POSITIVE LOGITS
    ultimate
    0.18
     pen
    0.15
    ning
    0.13
    Pen
    0.12
    manship
    0.12
     Pen
    0.12
    elope
    0.12
    acious
    0.11
     PEN
    0.10
    urious
    0.10
    Activations Density 0.004%

    No Known Activations