© 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. 15884
    Prev
    Next
    INDEX
    Explanations

    intricate finishing techniques

    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
     actionable
    -0.11
     packaged
    -0.11
     sanitized
    -0.11
     compil
    -0.11
     synthesized
    -0.10
     Succ
    -0.10
     proactive
    -0.10
    -self
    -0.10
     humiliating
    -0.10
     hosted
    -0.10
    POSITIVE LOGITS
     techniques
    0.20
     precision
    0.20
     technique
    0.20
     sculpt
    0.19
     skilled
    0.18
     painstaking
    0.17
     intricate
    0.17
     finish
    0.17
     finishing
    0.17
     Techniques
    0.16
    Activations Density 2.418%

    No Known Activations