© 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. 90855
    Prev
    Next
    INDEX
    Explanations

    neighbourhood, neighbor, social relations

    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
    emos
    -0.10
    ee
    -0.10
    fram
    -0.10
    ctor
    -0.08
    ej
    -0.08
    irie
    -0.08
    ema
    -0.08
    aura
    -0.08
    /to
    -0.08
    Ìģ
    -0.08
    POSITIVE LOGITS
    hood
    0.18
    liness
    0.15
    /global
    0.12
     hood
    0.12
    ial
    0.12
    /ne
    0.12
    oods
    0.12
    -ne
    0.11
    ship
    0.11
    ously
    0.11
    Activations Density 0.012%

    No Known Activations