© 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. 28064
    Prev
    Next
    INDEX
    Explanations

    coding=utf-8

    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
     Camb
    -0.09
     Bol
    -0.08
     contact
    -0.07
    bies
    -0.07
     patri
    -0.07
     tack
    -0.07
    footer
    -0.07
     cours
    -0.07
    anus
    -0.06
    iei
    -0.06
    POSITIVE LOGITS
    indo
    0.13
     CASCADE
    0.12
     Helm
    0.11
     Lem
    0.11
    alto
    0.11
    cen
    0.11
     Indoor
    0.11
    richt
    0.11
     Gunn
    0.11
    rette
    0.10
    Activations Density 0.004%

    No Known Activations