© 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. 31754
    Prev
    Next
    INDEX
    Explanations

    bubble variations

    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
    ened
    -0.10
    ures
    -0.09
    ening
    -0.09
    ings
    -0.09
    IVE
    -0.09
    esta
    -0.08
    samp
    -0.08
    ifu
    -0.08
    iac
    -0.08
    etime
    -0.08
    POSITIVE LOGITS
     Bubble
    0.21
     bubble
    0.20
    bubble
    0.19
     bubbles
    0.17
    Bubble
    0.17
     gum
    0.16
     Gum
    0.16
     bubb
    0.15
     balloon
    0.13
    wrap
    0.13
    Activations Density 0.017%

    No Known Activations