© 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. 6487
    Prev
    Next
    INDEX
    Explanations

    proximity to objects or concepts

    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
    olin
    -0.13
     penc
    -0.11
    asion
    -0.10
    allon
    -0.10
    adr
    -0.10
    InOut
    -0.10
    angi
    -0.10
    оÑĩ
    -0.09
    usto
    -0.09
    uh
    -0.09
    POSITIVE LOGITS
     nearest
    0.32
     closest
    0.31
    nearest
    0.18
    closest
    0.16
     opposite
    0.16
    (s
    0.15
     corresponding
    0.14
     nearer
    0.13
     designated
    0.13
     belonging
    0.12
    Activations Density 0.594%

    No Known Activations