© 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. 14602
    Prev
    Next
    INDEX
    Explanations

    balance of trade-offs

    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
     despite
    -0.10
     alongside
    -0.08
     nave
    -0.08
     aside
    -0.08
     Cass
    -0.08
     refr
    -0.07
     matrix
    -0.07
     Amid
    -0.07
     Despite
    -0.07
    matrix
    -0.07
    POSITIVE LOGITS
     elsewhere
    0.19
     compensated
    0.15
     compens
    0.14
     sheer
    0.13
     compensate
    0.13
     tw
    0.11
     gained
    0.11
     excess
    0.11
     ambition
    0.11
     regained
    0.11
    Activations Density 0.057%

    No Known Activations