© 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. 4026
    Prev
    Next
    INDEX
    Explanations

    words after parenthesis or specific tokens

    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
     gigg
    -0.11
     Innoc
    -0.10
     innocence
    -0.10
     chir
    -0.09
     innoc
    -0.09
     innocent
    -0.09
     naive
    -0.08
     Shame
    -0.08
     dem
    -0.08
     terror
    -0.08
    POSITIVE LOGITS
     gro
    0.17
     grit
    0.13
    gro
    0.13
    rox
    0.12
     grow
    0.12
     grunt
    0.12
     restr
    0.12
    æģ¯
    0.12
     forcibly
    0.11
    grow
    0.11
    Activations Density 0.029%

    No Known Activations