© 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. 17839
    Prev
    Next
    INDEX
    Explanations

    ring

    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
     textiles
    -0.12
    bundles
    -0.12
    otas
    -0.11
     fleece
    -0.11
    Leod
    -0.10
    xAC
    -0.10
    oho
    -0.10
     Arms
    -0.10
     stap
    -0.10
     vests
    -0.10
    POSITIVE LOGITS
     ring
    0.26
     Ring
    0.23
    Ring
    0.21
    -ring
    0.21
     rings
    0.19
    ring
    0.18
     finger
    0.18
    _ring
    0.17
    RING
    0.16
     Rings
    0.15
    Activations Density 0.128%

    No Known Activations