© 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. 91545
    Prev
    Next
    INDEX
    Explanations

    comparing conventional versus technical

    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
     mainland
    -0.22
     terrestrial
    -0.20
     mainstream
    -0.19
     heterosexual
    -0.16
     earthly
    -0.16
     civilian
    -0.16
     ordinary
    -0.15
     daytime
    -0.13
     adult
    -0.13
     ordin
    -0.13
    POSITIVE LOGITS
     paranormal
    0.16
     supernatural
    0.15
     abnormal
    0.14
     exotic
    0.14
     specialised
    0.13
     specialty
    0.13
     Specialty
    0.13
     specialized
    0.13
     fantast
    0.13
     fantasy
    0.13
    Activations Density 1.611%

    No Known Activations