© 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. 116778
    Prev
    Next
    INDEX
    Explanations

    branch of

    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
     atr
    -0.09
     raining
    -0.09
    /is
    -0.09
     Pry
    -0.09
     Spir
    -0.09
     Scre
    -0.09
     obvious
    -0.08
     tempting
    -0.08
    clo
    -0.08
    edis
    -0.08
    POSITIVE LOGITS
    uales
    0.11
    reno
    0.10
     Shack
    0.10
    Convention
    0.10
    ptype
    0.10
    []č↵
    0.10
    ever
    0.10
    imin
    0.10
    iero
    0.10
     Burgess
    0.10
    Activations Density 0.143%

    No Known Activations