© 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. 114907
    Prev
    Next
    INDEX
    Explanations

    have/has/have been + past participle

    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
    éro
    -0.11
     refer
    -0.11
    chas
    -0.11
    owered
    -0.11
    origin
    -0.11
    aket
    -0.10
    åħ¶ä¸Ń
    -0.10
    adel
    -0.10
    Originally
    -0.10
     reco
    -0.10
    POSITIVE LOGITS
     already
    0.18
     Already
    0.15
    already
    0.13
    Already
    0.11
     always
    0.10
     bereits
    0.09
    _already
    0.09
     finished
    0.08
     rarely
    0.08
    samp
    0.08
    Activations Density 0.070%

    No Known Activations