© 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. 14506
    Prev
    Next
    INDEX
    Explanations

    physical positions

    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
     stalk
    -0.08
     Vox
    -0.07
     yak
    -0.07
     extrad
    -0.07
     Pak
    -0.07
     NEO
    -0.07
     adm
    -0.07
     determination
    -0.07
     interv
    -0.07
     spec
    -0.07
    POSITIVE LOGITS
    eneg
    0.13
     parch
    0.12
     noses
    0.11
    Lang
    0.11
    jour
    0.11
     nose
    0.11
     Aware
    0.11
     Lesb
    0.11
     Hoy
    0.11
     unsus
    0.11
    Activations Density 0.021%

    No Known Activations