© 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. 114971
    Prev
    Next
    INDEX
    Explanations

    function and activity

    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
    mez
    -0.08
     Hann
    -0.07
    vb
    -0.07
     Vand
    -0.07
     resemble
    -0.07
    porte
    -0.07
     SP
    -0.07
    aton
    -0.07
     Alexand
    -0.07
    yme
    -0.07
    POSITIVE LOGITS
     activated
    0.20
     active
    0.17
     activations
    0.16
     functioning
    0.16
     activation
    0.15
     inactive
    0.15
    -active
    0.15
     malfunction
    0.15
     rust
    0.14
    activated
    0.14
    Activations Density 0.434%

    No Known Activations