© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3647
    Prev
    Next
    INDEX
    Explanations

    battery life and power

    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
     Ingram
    -0.11
    elib
    -0.10
     movable
    -0.10
     Verm
    -0.10
     Haz
    -0.10
     circ
    -0.10
     hend
    -0.09
    sea
    -0.09
    veh
    -0.09
    -inner
    -0.09
    POSITIVE LOGITS
     battery
    0.17
     recharge
    0.16
     Battery
    0.15
     depleted
    0.15
     depletion
    0.15
     drains
    0.13
    Battery
    0.13
     drain
    0.12
     Charge
    0.12
    battery
    0.12
    Activations Density 0.100%

    No Known Activations