© 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. 7406
    Prev
    Next
    INDEX
    Explanations

    choices and paths

    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
    akh
    -0.11
     Ker
    -0.10
     rhyth
    -0.09
    oso
    -0.09
     misrepresented
    -0.09
    upy
    -0.09
     abstract
    -0.09
    kr
    -0.09
    yro
    -0.09
    oser
    -0.09
    POSITIVE LOGITS
     branching
    0.40
     Branch
    0.32
     bran
    0.31
     branches
    0.31
     branch
    0.30
    Branch
    0.28
    branch
    0.28
     paths
    0.25
     choices
    0.25
    /Branch
    0.25
    Activations Density 0.653%

    No Known Activations