© 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. 88877
    Prev
    Next
    INDEX
    Explanations

    actions

    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
     negro
    -0.10
    atura
    -0.10
     PROVIDED
    -0.10
    ey
    -0.10
     Dud
    -0.10
     tir
    -0.09
    oup
    -0.09
    antaged
    -0.09
     Griff
    -0.09
     Claude
    -0.09
    POSITIVE LOGITS
    /actions
    0.23
     actions
    0.17
    (actions
    0.15
     Actions
    0.15
    actions
    0.14
    -actions
    0.13
    Actions
    0.13
     deeds
    0.12
    _actions
    0.12
    /activity
    0.12
    Activations Density 0.124%

    No Known Activations