© 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. 113670
    Prev
    Next
    INDEX
    Explanations

    start or finish

    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
     confirmation
    -0.08
     reprodu
    -0.08
     exh
    -0.08
     clar
    -0.08
     entire
    -0.08
     reuse
    -0.08
    oku
    -0.08
    ETH
    -0.08
     reproduced
    -0.08
     tightly
    -0.08
    POSITIVE LOGITS
     unfinished
    0.33
     incomplete
    0.28
     interrupted
    0.27
    unfinished
    0.27
     started
    0.21
     begun
    0.21
    Incomplete
    0.21
     initiated
    0.19
     Started
    0.18
     Interrupt
    0.18
    Activations Density 0.099%

    No Known Activations