© 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. 32953
    Prev
    Next
    INDEX
    Explanations

    File and label identification

    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
    
    -0.11
    heck
    -0.11
     arrang
    -0.11
    -0.10
    \↵
    -0.10
     Ernst
    -0.10
    aku
    -0.10
    eenth
    -0.10
     Swal
    -0.10
    &nbsp
    -0.10
    POSITIVE LOGITS
    0.09
     reco
    0.09
    oe
    0.08
    erset
    0.08
    DN
    0.08
    mit
    0.08
    аг
    0.07
     Jaime
    0.07
    -instance
    0.07
    terra
    0.07
    Activations Density 0.088%

    No Known Activations