© 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. 16013
    Prev
    Next
    INDEX
    Explanations

    image and figure citations

    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
     Wander
    -0.12
     huh
    -0.09
     chilling
    -0.09
     Rockefeller
    -0.09
     Cannes
    -0.09
     Bloody
    -0.08
     steer
    -0.08
    hei
    -0.08
    iego
    -0.08
    illas
    -0.08
    POSITIVE LOGITS
     tin
    0.09
     tops
    0.08
     Pair
    0.08
    tin
    0.08
     elev
    0.08
    mie
    0.07
    noc
    0.07
    iny
    0.07
     elevate
    0.07
    tor
    0.07
    Activations Density 0.011%

    No Known Activations