© 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. 46463
    Prev
    Next
    INDEX
    Explanations

    counterpart/counterparts

    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
     teammate
    -0.13
     colleague
    -0.10
     cowork
    -0.10
    aty
    -0.09
    another
    -0.08
     teammates
    -0.08
     member
    -0.08
    other
    -0.08
    aine
    -0.08
     tent
    -0.07
    POSITIVE LOGITS
     counterparts
    0.42
     counterpart
    0.40
     equivalents
    0.24
     counter
    0.22
    -counter
    0.22
     equivalent
    0.21
    counter
    0.20
     predecessors
    0.20
     Counter
    0.20
     cousins
    0.20
    Activations Density 0.057%

    No Known Activations