© 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. 5838
    Prev
    Next
    INDEX
    Explanations

    personal experience or possession

    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
    ntax
    -0.10
    igner
    -0.10
    stoi
    -0.10
    /if
    -0.10
    htdocs
    -0.10
     backs
    -0.10
     ensuing
    -0.10
     PAGE
    -0.10
    lesi
    -0.10
     Invocation
    -0.10
    POSITIVE LOGITS
     recently
    0.14
     personally
    0.11
     two
    0.10
     reviewed
    0.10
     tested
    0.09
    IH
    0.09
     Personally
    0.09
     friendships
    0.09
     tried
    0.09
     myself
    0.09
    Activations Density 0.152%

    No Known Activations