© 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. 16087
    Prev
    Next
    INDEX
    Explanations

    request for help or relief

    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
    zet
    -0.13
     Lace
    -0.11
     momentarily
    -0.10
    meld
    -0.10
     contin
    -0.09
     vere
    -0.09
    660
    -0.09
     ordin
    -0.09
     Amendments
    -0.09
    unks
    -0.09
    POSITIVE LOGITS
     distraction
    0.12
     satisfying
    0.11
     cheering
    0.11
     escap
    0.11
     refresh
    0.11
     reass
    0.11
    -refresh
    0.10
     relief
    0.10
     outlet
    0.10
     vacation
    0.09
    Activations Density 0.029%

    No Known Activations