© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90176
    Prev
    Next
    INDEX
    Explanations

    describing intense phenomena

    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
    rá
    -0.11
    ded
    -0.10
     Sof
    -0.09
     lingering
    -0.09
     Dw
    -0.09
    ship
    -0.08
     Franc
    -0.08
    dens
    -0.08
    jan
    -0.08
    mana
    -0.08
    POSITIVE LOGITS
    ingly
    0.21
    -hot
    0.19
    -eyed
    0.14
     hot
    0.13
    -mouth
    0.13
    -white
    0.13
    ly
    0.12
    -fast
    0.12
    hot
    0.11
     mess
    0.11
    Activations Density 0.048%

    No Known Activations