© 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. 89448
    Prev
    Next
    INDEX
    Explanations

    availability and missing information

    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
    iger
    -0.11
    vox
    -0.11
     iota
    -0.10
    minus
    -0.10
    nÃŃ
    -0.10
    -medium
    -0.10
    .press
    -0.10
     Tour
    -0.10
     Tours
    -0.10
    flies
    -0.10
    POSITIVE LOGITS
     favor
    0.09
     rooting
    0.09
     Fence
    0.08
     saturated
    0.08
    ungan
    0.08
     hyster
    0.07
     abst
    0.07
     ident
    0.07
     Favor
    0.07
     favors
    0.07
    Activations Density 0.001%

    No Known Activations