© 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. 47372
    Prev
    Next
    INDEX
    Explanations

    states of being

    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
     belonging
    -0.09
     previously
    -0.09
     hired
    -0.09
     Mig
    -0.09
    iosk
    -0.09
     skilled
    -0.09
     emptied
    -0.09
     wid
    -0.08
     formerly
    -0.08
     dreaded
    -0.08
    POSITIVE LOGITS
    /w
    0.16
     gone
    0.16
     alive
    0.14
     definitely
    0.14
     intact
    0.13
     undergoing
    0.13
     showing
    0.12
     behaving
    0.12
    otope
    0.12
     going
    0.12
    Activations Density 0.072%

    No Known Activations