© 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. 5500
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency or degree

    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
    698
    -0.09
     Eaton
    -0.09
    /h
    -0.08
    est
    -0.08
     unbiased
    -0.08
    alc
    -0.08
    оÑĤоÑĢ
    -0.08
     granularity
    -0.08
    imon
    -0.07
     Nem
    -0.07
    POSITIVE LOGITS
    iling
    0.10
     additionally
    0.10
    erson
    0.10
    iser
    0.10
     Tok
    0.10
     specifically
    0.10
     ust
    0.10
    172
    0.09
     ideally
    0.09
     firstly
    0.09
    Activations Density 0.209%

    No Known Activations