© 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. 6457
    Prev
    Next
    INDEX
    Explanations

    secret passages and hidden places

    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
     populated
    -0.10
     rede
    -0.09
     cruc
    -0.09
    dk
    -0.09
     distant
    -0.09
    601
    -0.08
     encount
    -0.08
     populate
    -0.08
    506
    -0.08
     curry
    -0.08
    POSITIVE LOGITS
     secret
    0.25
     hidden
    0.24
     concealed
    0.24
    secret
    0.20
     Hidden
    0.20
     Secret
    0.20
    -secret
    0.20
     conceal
    0.19
    Hidden
    0.18
     disguised
    0.18
    Activations Density 0.115%

    No Known Activations