© 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. 113434
    Prev
    Next
    INDEX
    Explanations

    dev related terms

    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
    .ActionListener
    -0.12
     developments
    -0.12
     developed
    -0.10
     develops
    -0.09
     Developed
    -0.09
     Colomb
    -0.08
    _decrypt
    -0.08
    develop
    -0.08
     Develop
    -0.08
    _validator
    -0.08
    POSITIVE LOGITS
     dev
    0.14
    /dev
    0.12
    .Dev
    0.11
     pitch
    0.11
     Dev
    0.11
    Dev
    0.10
    (dev
    0.09
    wort
    0.09
    ingroup
    0.09
    dev
    0.08
    Activations Density 0.307%

    No Known Activations