© 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. 4052
    Prev
    Next
    INDEX
    Explanations

    exploration of

    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
    ha
    -0.09
     litt
    -0.09
    emd
    -0.08
    alter
    -0.08
    etting
    -0.08
     handling
    -0.08
     contents
    -0.08
    ed
    -0.08
    PointCloud
    -0.08
    ael
    -0.08
    POSITIVE LOGITS
     exploration
    0.18
     explor
    0.16
     voy
    0.14
     spirit
    0.13
     Exploration
    0.12
     INTO
    0.12
     undertaken
    0.11
     exploring
    0.11
     voyage
    0.11
    rary
    0.11
    Activations Density 0.018%

    No Known Activations