© 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. 112263
    Prev
    Next
    INDEX
    Explanations

    getting ready

    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
    jal
    -0.10
    ako
    -0.09
     Ames
    -0.08
    enna
    -0.08
    amon
    -0.08
    /run
    -0.07
     sever
    -0.07
    ãĥĬ
    -0.07
     holding
    -0.07
     Apocalypse
    -0.07
    POSITIVE LOGITS
     ready
    0.28
     Ready
    0.19
    ready
    0.18
     READY
    0.16
     underway
    0.14
     out
    0.14
    Ready
    0.14
     back
    0.14
    -ready
    0.14
     prepared
    0.13
    Activations Density 0.107%

    No Known Activations