© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89508
    Prev
    Next
    INDEX
    Explanations

    bender, ballasts, vaporizers, heater, modulator, rest, mass, bus, screwdriver

    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
    itous
    -0.12
    ously
    -0.11
     Soul
    -0.11
     soul
    -0.11
     duplic
    -0.11
    ufen
    -0.10
    eous
    -0.10
    antics
    -0.10
    bpp
    -0.10
    ción
    -0.10
    POSITIVE LOGITS
    ses
    0.12
     massage
    0.12
    massage
    0.10
     relaxation
    0.09
    åĻ¨
    0.09
     Seventh
    0.09
    mall
    0.09
     machines
    0.09
    agn
    0.09
    acam
    0.09
    Activations Density 0.008%

    No Known Activations