© 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. 31017
    Prev
    Next
    INDEX
    Explanations

    controlled study/experiment

    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
    aison
    -0.09
    lider
    -0.09
     mistaken
    -0.09
     spies
    -0.08
    arna
    -0.08
    936
    -0.08
    isol
    -0.08
    oss
    -0.08
     communicating
    -0.08
     thirsty
    -0.08
    POSITIVE LOGITS
     controlled
    0.15
     chaos
    0.15
    -release
    0.13
     Controlled
    0.13
    controlled
    0.13
    /un
    0.13
    /form
    0.12
     environment
    0.12
     environments
    0.11
     Chaos
    0.11
    Activations Density 0.253%

    No Known Activations