© 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. 91851
    Prev
    Next
    INDEX
    Explanations

    adding or joining people/things

    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
    ara
    -0.11
     personally
    -0.10
    endi
    -0.10
    ior
    -0.10
    endor
    -0.09
    bid
    -0.09
    alla
    -0.08
     exhib
    -0.08
     Dob
    -0.08
     coup
    -0.08
    POSITIVE LOGITS
     joining
    0.20
     join
    0.20
     joins
    0.18
     joined
    0.17
     Join
    0.17
    _join
    0.15
     added
    0.15
    joining
    0.15
    Join
    0.15
    join
    0.15
    Activations Density 0.053%

    No Known Activations