© 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. 7545
    Prev
    Next
    INDEX
    Explanations

    have good preparation

    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
     Pav
    -0.12
    amas
    -0.10
    elig
    -0.10
    ilha
    -0.10
     Manning
    -0.10
     involuntary
    -0.10
     franch
    -0.10
    ugi
    -0.09
    elier
    -0.09
     unfamiliar
    -0.09
    POSITIVE LOGITS
     adequate
    0.17
     backup
    0.17
     sufficient
    0.17
     backups
    0.16
     Backup
    0.16
     proper
    0.15
     knowledge
    0.14
     patience
    0.14
     clear
    0.14
     clarity
    0.13
    Activations Density 0.087%

    No Known Activations