© 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. 15782
    Prev
    Next
    INDEX
    Explanations

    was followed by past events or descriptions

    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
     currently
    -0.11
    /w
    -0.10
     definitely
    -0.09
     certainly
    -0.08
     indeed
    -0.08
    -X
    -0.07
     Pai
    -0.07
     hereby
    -0.07
    rael
    -0.07
     personals
    -0.07
    POSITIVE LOGITS
    abi
    0.15
    p
    0.14
    ylko
    0.13
    htub
    0.13
     kost
    0.12
    /is
    0.12
    ps
    0.11
     previously
    0.11
    atch
    0.11
     pres
    0.11
    Activations Density 0.278%

    No Known Activations