© 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. 25750
    Prev
    Next
    INDEX
    Explanations

    how they interact

    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
     starred
    -0.10
     purge
    -0.09
     sensation
    -0.09
     feels
    -0.08
    undle
    -0.08
     sensations
    -0.08
     fores
    -0.08
    á»ĭ
    -0.08
     vict
    -0.08
     FT
    -0.08
    POSITIVE LOGITS
     interaction
    0.29
     interactions
    0.27
     Interaction
    0.25
     interacting
    0.25
    interaction
    0.24
     interact
    0.24
    Interaction
    0.24
     interacts
    0.22
    _interaction
    0.17
     rapport
    0.16
    Activations Density 0.057%

    No Known Activations