© 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. 5263
    Prev
    Next
    INDEX
    Explanations

    counterparts or vice versa

    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
     compared
    -0.14
     alongside
    -0.13
     Himself
    -0.11
     Yourself
    -0.10
    comp
    -0.10
     Vs
    -0.10
     yourselves
    -0.10
     vs
    -0.10
     Compared
    -0.10
    _vs
    -0.10
    POSITIVE LOGITS
     counterparts
    0.14
     counterpart
    0.14
     ones
    0.13
     vice
    0.12
    ones
    0.10
    unga
    0.09
     BOTH
    0.09
    lace
    0.09
     recip
    0.09
     Carp
    0.09
    Activations Density 1.432%

    No Known Activations