© 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. 4030
    Prev
    Next
    INDEX
    Explanations

    well known/documented/regarded

    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
    ién
    -0.09
     Ded
    -0.09
    |m
    -0.08
    pes
    -0.08
    (Program
    -0.08
    |x
    -0.08
    mq
    -0.08
    endant
    -0.08
    iner
    -0.08
    |i
    -0.08
    POSITIVE LOGITS
     beyond
    0.13
     worth
    0.13
     past
    0.12
     underway
    0.12
     below
    0.11
    Chuck
    0.11
     Sweat
    0.11
     authenticated
    0.10
     att
    0.10
     Cory
    0.10
    Activations Density 0.040%

    No Known Activations