© 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. 5859
    Prev
    Next
    INDEX
    Explanations

    left or right step

    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
     upright
    -0.11
    slack
    -0.09
    /Dk
    -0.08
     lod
    -0.08
    slick
    -0.08
     Anc
    -0.08
    -any
    -0.08
    anche
    -0.07
     respect
    -0.07
    hape
    -0.07
    POSITIVE LOGITS
     alternating
    0.18
     continuous
    0.16
     continuously
    0.16
     rapid
    0.14
     rapidly
    0.14
     Altern
    0.14
     slowly
    0.14
     gradual
    0.13
    Altern
    0.13
     Continuous
    0.13
    Activations Density 0.036%

    No Known Activations