© 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. 4144
    Prev
    Next
    INDEX
    Explanations

    electric, voltage,

    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
     Hoe
    -0.09
    mia
    -0.09
    aho
    -0.09
     hoe
    -0.09
     Olive
    -0.09
    dao
    -0.09
    Credential
    -0.09
    rut
    -0.08
     Cypress
    -0.08
    redo
    -0.08
    POSITIVE LOGITS
     electricity
    0.18
     electric
    0.17
     Electricity
    0.17
     voltage
    0.17
     electrical
    0.16
     élect
    0.15
     wires
    0.15
    electric
    0.15
     Electric
    0.15
    -elect
    0.14
    Activations Density 0.416%

    No Known Activations