© 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. 14471
    Prev
    Next
    INDEX
    Explanations

    I

    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
     initially
    -0.11
     thereafter
    -0.11
     originally
    -0.11
     soon
    -0.10
     suddenly
    -0.10
     cach
    -0.10
     presently
    -0.10
     Pol
    -0.09
    xe
    -0.09
    qua
    -0.09
    POSITIVE LOGITS
     wonder
    0.12
    icon
    0.10
     pinpoint
    0.10
     wondering
    0.10
     trace
    0.09
    uite
    0.09
     wondered
    0.09
     marvel
    0.09
     bri
    0.09
     pivotal
    0.09
    Activations Density 0.034%

    No Known Activations