© 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. 88417
    Prev
    Next
    INDEX
    Explanations

    carrying or carried

    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
     raise
    -0.10
     Raise
    -0.10
     Hold
    -0.09
    sWith
    -0.09
    raised
    -0.09
    Raise
    -0.09
     neighb
    -0.09
    bib
    -0.09
    ulle
    -0.09
    bz
    -0.09
    POSITIVE LOGITS
    avel
    0.12
     scars
    0.10
     stacks
    0.10
     traces
    0.10
     copies
    0.09
    zym
    0.09
    tep
    0.09
     buckets
    0.08
    -on
    0.08
     blot
    0.08
    Activations Density 0.026%

    No Known Activations