© 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. 31877
    Prev
    Next
    INDEX
    Explanations

    first appearances or states

    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
     reunited
    -0.09
     Back
    -0.08
    yz
    -0.07
    ero
    -0.07
    blas
    -0.07
     av
    -0.07
    eth
    -0.06
    Back
    -0.06
    725
    -0.06
    mes
    -0.06
    POSITIVE LOGITS
     earm
    0.13
     status
    0.13
     gib
    0.12
    -status
    0.12
    solete
    0.12
     Hunter
    0.12
    hire
    0.12
    inars
    0.12
    ocaly
    0.12
    Hunter
    0.11
    Activations Density 0.003%

    No Known Activations