© 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. 48511
    Prev
    Next
    INDEX
    Explanations

    proximity together

    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
     belonging
    -0.12
     Keller
    -0.10
     belong
    -0.10
    Liked
    -0.10
     marca
    -0.10
    zu
    -0.10
     excursion
    -0.10
    hardt
    -0.10
    azo
    -0.09
    463
    -0.09
    POSITIVE LOGITS
     alongside
    0.24
     surrounded
    0.21
     proximity
    0.17
     beside
    0.13
     junto
    0.12
     surround
    0.12
     adjacent
    0.12
     Surround
    0.12
     near
    0.12
     together
    0.11
    Activations Density 0.135%

    No Known Activations