© 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. 7373
    Prev
    Next
    INDEX
    Explanations

    vs, versus, and

    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
    /navigation
    -0.09
    �t
    -0.08
    -type
    -0.08
    -rate
    -0.07
    -shaped
    -0.07
    -setting
    -0.06
    -format
    -0.06
    icker
    -0.06
    -groups
    -0.06
    /activity
    -0.06
    POSITIVE LOGITS
    -to
    0.29
    -vs
    0.28
     vs
    0.27
     <->
    0.26
     âĨĶ
    0.25
    _vs
    0.24
     versus
    0.23
    –
    0.23
    -vers
    0.22
    -and
    0.20
    Activations Density 2.068%

    No Known Activations