© 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. 28090
    Prev
    Next
    INDEX
    Explanations

    file paths and errors

    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
    ukan
    -0.10
    beck
    -0.09
     exploits
    -0.09
     imper
    -0.09
    wins
    -0.09
    /me
    -0.08
     fearless
    -0.08
     contention
    -0.08
    TK
    -0.08
     excited
    -0.08
    POSITIVE LOGITS
     apologies
    0.15
     apology
    0.15
     apolog
    0.14
     apologize
    0.14
     apologise
    0.14
     begged
    0.13
     plea
    0.13
     apologized
    0.13
     future
    0.12
    pled
    0.12
    Activations Density 0.003%

    No Known Activations