© 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. 18094
    Prev
    Next
    INDEX
    Explanations

    physical demands to promise

    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
     purchases
    -0.07
    ibi
    -0.07
     finances
    -0.07
     depression
    -0.07
    ug
    -0.07
    staw
    -0.07
    ego
    -0.07
    ond
    -0.07
    960
    -0.07
     affection
    -0.07
    POSITIVE LOGITS
    foundland
    0.11
     notwithstanding
    0.11
     Nun
    0.11
    inee
    0.11
    �t
    0.10
     tw
    0.10
     accompanying
    0.10
     nun
    0.10
     corresponding
    0.10
     neighboring
    0.10
    Activations Density 0.682%

    No Known Activations