© 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. 6762
    Prev
    Next
    INDEX
    Explanations

    2015, 2016, 2017, 2019

    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
     ag
    -0.12
    jing
    -0.11
     sol
    -0.11
    idor
    -0.11
     Sol
    -0.11
    tur
    -0.11
     ad
    -0.10
     Griff
    -0.10
    sol
    -0.10
    lite
    -0.10
    POSITIVE LOGITS
     Alter
    0.09
    vent
    0.08
     altered
    0.08
     Fac
    0.08
    vents
    0.07
    onis
    0.07
     Uns
    0.07
    ervas
    0.07
     Ventura
    0.07
     hypers
    0.07
    Activations Density 0.237%

    No Known Activations