© 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. 111875
    Prev
    Next
    INDEX
    Explanations

    Once again

    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
     Warn
    -0.11
    ille
    -0.10
    irk
    -0.10
    ï¼Īç¬ij
    -0.10
     uncont
    -0.10
     undert
    -0.10
    685
    -0.10
    ity
    -0.10
    _runs
    -0.10
     repmat
    -0.10
    POSITIVE LOGITS
     Upon
    0.20
     upon
    0.19
    Upon
    0.16
    upon
    0.13
     Broad
    0.07
    ç½
    0.07
    "|
    0.07
     spre
    0.07
    charg
    0.07
    adol
    0.07
    Activations Density 0.008%

    No Known Activations