© 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. 32738
    Prev
    Next
    INDEX
    Explanations

    atomic related terms and actions

    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
     Sin
    -0.09
    ICT
    -0.09
    tok
    -0.09
    jak
    -0.09
     triple
    -0.09
     Rhodes
    -0.09
     Balk
    -0.09
    xDA
    -0.09
     innoc
    -0.08
    AGR
    -0.08
    POSITIVE LOGITS
    ulum
    0.10
    usu
    0.10
    opup
    0.10
    duk
    0.10
     bun
    0.10
     honoured
    0.09
     âĦĸ
    0.09
    vant
    0.09
     backlog
    0.09
    orte
    0.09
    Activations Density 0.002%

    No Known Activations