© 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. 90032
    Prev
    Next
    INDEX
    Explanations

    greetings and introductions

    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
     Excell
    -0.10
     elders
    -0.10
    Granted
    -0.09
     delights
    -0.09
     Concord
    -0.09
    Fred
    -0.09
     Luz
    -0.09
     Norris
    -0.09
     Eld
    -0.09
     imm
    -0.09
    POSITIVE LOGITS
     Hi
    0.12
     Welcome
    0.11
     hi
    0.11
    Welcome
    0.11
     Hey
    0.11
     Hello
    0.10
     hello
    0.10
    ãģĵãĤĵãģ«
    0.10
    welcome
    0.09
    YOUR
    0.09
    Activations Density 0.007%

    No Known Activations