© 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. 17328
    Prev
    Next
    INDEX
    Explanations

    joining and belonging

    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
     steward
    -0.12
    owie
    -0.10
     stew
    -0.10
     Encounter
    -0.09
    trak
    -0.09
    ÑģÑĭ
    -0.09
    bia
    -0.09
    meter
    -0.09
     opposing
    -0.09
    pairs
    -0.09
    POSITIVE LOGITS
     joining
    0.31
     belonging
    0.29
     join
    0.29
     belong
    0.27
     Join
    0.27
     membership
    0.26
     joins
    0.26
    joining
    0.25
     fitting
    0.25
     accepted
    0.24
    Activations Density 0.273%

    No Known Activations