© 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. 29346
    Prev
    Next
    INDEX
    Explanations

    no

    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
     whatsoever
    -0.10
     nor
    -0.10
     contemplating
    -0.08
     Bew
    -0.08
     suspect
    -0.07
    +A
    -0.07
    æ»
    -0.07
    Vault
    -0.07
     linger
    -0.07
     Mirror
    -0.07
    POSITIVE LOGITS
     noc
    0.12
     kings
    0.12
    eded
    0.11
    agini
    0.11
    duce
    0.11
     Wol
    0.11
    .addTarget
    0.10
     desn
    0.10
     dese
    0.10
    imed
    0.10
    Activations Density 0.019%

    No Known Activations