© 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. 114501
    Prev
    Next
    INDEX
    Explanations

    metadata and navigation elements

    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
     prem
    -0.10
    ille
    -0.08
    ansa
    -0.08
    ike
    -0.08
    ales
    -0.07
     ries
    -0.07
    iken
    -0.07
    rike
    -0.07
     [][]
    -0.07
     Lindsey
    -0.07
    POSITIVE LOGITS
    arth
    0.12
    %=
    0.11
     Naw
    0.10
    arer
    0.10
    raj
    0.10
     bios
    0.10
    bare
    0.10
     sucker
    0.10
    kal
    0.10
    bios
    0.09
    Activations Density 0.429%

    No Known Activations