© 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. 116927
    Prev
    Next
    INDEX
    Explanations

    section headers starting with Archives:

    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
    itsu
    -0.11
    tml
    -0.11
    achu
    -0.11
    sWith
    -0.11
    reso
    -0.11
     seit
    -0.11
    acho
    -0.11
     Rae
    -0.10
     Bravo
    -0.10
    waves
    -0.10
    POSITIVE LOGITS
     Bark
    0.08
     plat
    0.08
     sufficiently
    0.08
     selectable
    0.07
     classified
    0.07
     ply
    0.07
    retch
    0.07
    contin
    0.07
     constraint
    0.07
     brand
    0.07
    Activations Density 0.006%

    No Known Activations