© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90676
    Prev
    Next
    INDEX
    Explanations

    charge, advance, storm

    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
    opp
    -0.11
     McDon
    -0.10
    ayah
    -0.09
    rots
    -0.09
     Bew
    -0.09
    miss
    -0.09
    PN
    -0.09
     Burnett
    -0.09
     teased
    -0.09
     dece
    -0.09
    POSITIVE LOGITS
     forward
    0.22
     ahead
    0.21
    -ahead
    0.20
     charging
    0.19
     charge
    0.18
     Charge
    0.17
     Charging
    0.17
    -forward
    0.16
     Ahead
    0.16
    Forward
    0.16
    Activations Density 0.021%

    No Known Activations