© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48185
    Prev
    Next
    INDEX
    Explanations

    timing words: any_way, after_wards, now_a_days

    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
    ete
    -0.08
     cin
    -0.08
     nor
    -0.07
    whose
    -0.07
    —including
    -0.07
    OO
    -0.07
    avad
    -0.07
    which
    -0.06
     ?????
    -0.06
     plat
    -0.06
    POSITIVE LOGITS
     anyway
    0.30
     anyways
    0.28
     anyhow
    0.26
     btw
    0.22
     afterwards
    0.21
     afterward
    0.20
     respectively
    0.19
     meanwhile
    0.19
     nowadays
    0.19
     nonetheless
    0.18
    Activations Density 0.949%

    No Known Activations