© 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. 27377
    Prev
    Next
    INDEX
    Explanations

    hidden or unseen location

    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
     noticeable
    -0.09
     Brandon
    -0.09
     Caj
    -0.09
     Flags
    -0.09
     looph
    -0.08
     Barr
    -0.08
     branded
    -0.08
     unmistak
    -0.08
    quin
    -0.08
     clearly
    -0.08
    POSITIVE LOGITS
     unseen
    0.31
     hidden
    0.28
     concealed
    0.23
    -hidden
    0.22
     Hidden
    0.21
    hidden
    0.21
    Hidden
    0.20
     unknown
    0.20
     hiding
    0.19
     invisible
    0.19
    Activations Density 0.087%

    No Known Activations