© 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. 88432
    Prev
    Next
    INDEX
    Explanations

    "virtual" or "routed" or "link" or "first"

    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
     alas
    -0.09
     outdoors
    -0.09
    owe
    -0.09
     mainstream
    -0.09
     toys
    -0.09
     older
    -0.09
     heterosexual
    -0.09
     somehow
    -0.09
     margins
    -0.08
     relatively
    -0.08
    POSITIVE LOGITS
     Reverse
    0.12
     pseudo
    0.11
     -*
    0.11
     mini
    0.11
    Reverse
    0.10
     instant
    0.10
     reverse
    0.10
    umpt
    0.10
    reverse
    0.09
     positional
    0.09
    Activations Density 0.425%

    No Known Activations