© 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. 112998
    Prev
    Next
    INDEX
    Explanations

    initial phases of processes

    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
     componentDidUpdate
    -0.13
     Continuing
    -0.11
     continuing
    -0.10
    dae
    -0.09
    irate
    -0.09
    output
    -0.09
     Output
    -0.09
     resale
    -0.09
     Zh
    -0.08
    .jobs
    -0.08
    POSITIVE LOGITS
     initial
    0.30
     Initial
    0.28
    initial
    0.25
    Initial
    0.25
     prepar
    0.23
    .initial
    0.22
     initiation
    0.22
     initially
    0.22
    -initial
    0.21
    _initial
    0.21
    Activations Density 1.817%

    No Known Activations