© 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. 50034
    Prev
    Next
    INDEX
    Explanations

    locations and regions

    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
     Splash
    -0.12
    اد
    -0.11
     separator
    -0.10
     subrange
    -0.10
     Frag
    -0.10
     innocent
    -0.10
    Splash
    -0.10
     semif
    -0.10
     Flake
    -0.10
     splash
    -0.09
    POSITIVE LOGITS
     spots
    0.14
     located
    0.11
     identified
    0.11
     anatomy
    0.10
     map
    0.10
    spots
    0.10
     locations
    0.10
     areas
    0.09
     stimulation
    0.09
     hidden
    0.09
    Activations Density 0.148%

    No Known Activations