© 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. 33199
    Prev
    Next
    INDEX
    Explanations

    visible or not visible

    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
     unf
    -0.11
     targ
    -0.10
    iac
    -0.10
    onica
    -0.09
    zer
    -0.09
    hin
    -0.09
    ACA
    -0.09
    alla
    -0.09
    uard
    -0.09
     stead
    -0.09
    POSITIVE LOGITS
     visible
    0.34
     Visible
    0.27
     visibility
    0.25
     observable
    0.24
    visible
    0.24
    -visible
    0.23
     glimps
    0.23
    Visible
    0.22
     discern
    0.21
     Visibility
    0.21
    Activations Density 0.181%

    No Known Activations