© 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. 89132
    Prev
    Next
    INDEX
    Explanations

    state endings

    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
     surviving
    -0.08
    angan
    -0.08
     fest
    -0.08
    /body
    -0.08
    ilder
    -0.07
     [*
    -0.07
     remaining
    -0.07
     Pound
    -0.07
     contents
    -0.07
     incarn
    -0.07
    POSITIVE LOGITS
    /single
    0.15
     remar
    0.13
    /dis
    0.11
    dings
    0.10
    /div
    0.09
    recent
    0.09
    _recent
    0.09
    /D
    0.09
     Hubb
    0.09
    bih
    0.09
    Activations Density 0.005%

    No Known Activations