© 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. 32684
    Prev
    Next
    INDEX
    Explanations

    contractions and sentence endings

    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
     partially
    -0.09
     ap
    -0.09
     profess
    -0.09
    -fashion
    -0.09
    lah
    -0.08
     loosely
    -0.08
     bef
    -0.08
     Nah
    -0.08
     Poz
    -0.08
     fairly
    -0.08
    POSITIVE LOGITS
    ’T
    0.11
    scribed
    0.09
     Kro
    0.09
     Garner
    0.09
    ALER
    0.09
    ’S
    0.09
     Kurd
    0.09
     svo
    0.09
    pei
    0.08
    alth
    0.08
    Activations Density 0.130%

    No Known Activations