© 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. 30836
    Prev
    Next
    INDEX
    Explanations

    wire-related contexts

    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
    /Error
    -0.11
    yer
    -0.11
    sert
    -0.10
    upplier
    -0.10
    ouri
    -0.10
     jack
    -0.09
    oir
    -0.09
    sWith
    -0.09
     Tight
    -0.09
     slim
    -0.09
    POSITIVE LOGITS
    frame
    0.15
    lessly
    0.12
    frames
    0.10
    tap
    0.10
     ment
    0.10
    LESS
    0.10
    craft
    0.09
    guard
    0.09
    less
    0.09
    bound
    0.09
    Activations Density 0.018%

    No Known Activations