© 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. 48360
    Prev
    Next
    INDEX
    Explanations

    worked with or on

    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
    yy
    -0.08
     ob
    -0.08
     spontaneously
    -0.08
     endanger
    -0.07
     candidates
    -0.06
     destroyer
    -0.06
     eventual
    -0.06
     inher
    -0.06
     spontaneous
    -0.06
    ¦
    -0.06
    POSITIVE LOGITS
     worked
    0.25
     working
    0.21
    worked
    0.21
    working
    0.20
    Working
    0.18
     WORK
    0.18
     ÑĢабоÑĤ
    0.17
     Working
    0.17
    -working
    0.17
    /work
    0.17
    Activations Density 0.004%

    No Known Activations