© 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. 48050
    Prev
    Next
    INDEX
    Explanations

    regained control or position

    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
    reta
    -0.11
    ooter
    -0.10
     Fran
    -0.10
    /array
    -0.10
     disemb
    -0.09
    goto
    -0.09
    oler
    -0.09
    oni
    -0.09
     appeals
    -0.09
     reinforcement
    -0.09
    POSITIVE LOGITS
     control
    0.16
     footing
    0.15
     lost
    0.15
     equilibrium
    0.13
    Lost
    0.12
     Lost
    0.12
     balance
    0.12
    control
    0.12
     com
    0.12
     posture
    0.12
    Activations Density 0.009%

    No Known Activations