© 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. 114350
    Prev
    Next
    INDEX
    Explanations

    felt followed by adjectives or participial 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
    ings
    -0.13
    ho
    -0.12
    ohl
    -0.12
    ANCE
    -0.12
    erin
    -0.11
    ity
    -0.11
    ermo
    -0.11
     Burgess
    -0.11
    hive
    -0.10
    ingo
    -0.10
    POSITIVE LOGITS
    ed
    0.23
    ted
    0.14
    ting
    0.14
    edb
    0.11
    tings
    0.11
    cha
    0.10
    icha
    0.10
    edBy
    0.09
    ti
    0.09
    orious
    0.09
    Activations Density 0.006%

    No Known Activations