© 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. 16226
    Prev
    Next
    INDEX
    Explanations

    licensed.trans

    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
     nond
    -0.13
    -margin
    -0.11
     balk
    -0.10
    indy
    -0.10
    -ing
    -0.10
    /opt
    -0.09
    argin
    -0.09
    edin
    -0.09
    /shared
    -0.09
     Fil
    -0.09
    POSITIVE LOGITS
     peripherals
    0.10
     Reserve
    0.09
    contro
    0.09
     verse
    0.09
    etat
    0.09
     hypnot
    0.09
     mesmer
    0.09
     Wor
    0.08
     Interstate
    0.08
     reserve
    0.08
    Activations Density 0.001%

    No Known Activations