© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 116816
    Prev
    Next
    INDEX
    Explanations

    the invention relates to

    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
    ooth
    -0.11
    shaw
    -0.10
    728
    -0.10
    yah
    -0.10
     Breath
    -0.10
    uchen
    -0.10
     nett
    -0.10
    aces
    -0.10
     undert
    -0.09
    yu
    -0.09
    POSITIVE LOGITS
     Benefits
    0.09
     benefits
    0.09
     easiest
    0.08
     perks
    0.08
     right
    0.08
     beauty
    0.08
    aban
    0.08
     conver
    0.08
     hairy
    0.08
     benefit
    0.08
    Activations Density 0.001%

    No Known Activations