© 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. 117068
    Prev
    Next
    INDEX
    Explanations

    dimension, angles, expand

    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
    jos
    -0.11
    /from
    -0.11
    tran
    -0.10
    TION
    -0.10
    uman
    -0.10
    /on
    -0.10
    /original
    -0.09
    PMC
    -0.09
    ording
    -0.09
    chap
    -0.09
    POSITIVE LOGITS
     altern
    0.11
    ilet
    0.10
    angles
    0.09
     gadget
    0.08
    atu
    0.08
     dimension
    0.08
     depending
    0.08
     Tart
    0.08
     extrad
    0.08
     Fal
    0.08
    Activations Density 0.028%

    No Known Activations