© 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. 7564
    Prev
    Next
    INDEX
    Explanations

    numbers with units or descriptions

    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
     Benchmark
    -0.09
     Root
    -0.08
    ASM
    -0.08
    COPY
    -0.08
     session
    -0.08
     Crab
    -0.08
    ARP
    -0.08
     creeping
    -0.08
    odus
    -0.08
     Koh
    -0.08
    POSITIVE LOGITS
    fone
    0.11
     dispos
    0.10
     bom
    0.10
     slack
    0.10
     dilig
    0.10
     Caval
    0.10
    inel
    0.09
    olon
    0.09
    aida
    0.09
     Bos
    0.09
    Activations Density 0.002%

    No Known Activations