© 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. 4208
    Prev
    Next
    INDEX
    Explanations

    propelled forward

    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
     bells
    -0.09
    uali
    -0.09
    rego
    -0.09
    anke
    -0.09
    orch
    -0.09
    anners
    -0.08
    -dismiss
    -0.08
    igar
    -0.08
    duk
    -0.08
     Flam
    -0.08
    POSITIVE LOGITS
     forward
    0.24
     propelled
    0.21
     catapult
    0.19
     Forward
    0.19
    forward
    0.18
    Forward
    0.17
     FORWARD
    0.17
     forwards
    0.17
     propel
    0.17
     onward
    0.16
    Activations Density 0.032%

    No Known Activations