© 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. 91291
    Prev
    Next
    INDEX
    Explanations

    fasten or secure things

    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
     enf
    -0.10
     Hills
    -0.09
     inward
    -0.09
    ele
    -0.09
    actors
    -0.09
     aloud
    -0.09
     nud
    -0.09
     Sears
    -0.09
    quirer
    -0.09
    ez
    -0.08
    POSITIVE LOGITS
     firmly
    0.16
     nailed
    0.16
     onto
    0.14
     peg
    0.14
     pinned
    0.14
     elusive
    0.13
     Pins
    0.12
     pins
    0.12
    åĪ°
    0.11
     securely
    0.11
    Activations Density 0.054%

    No Known Activations