© 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. 18236
    Prev
    Next
    INDEX
    Explanations

    negative expletives

    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
    e
    -0.17
    s
    -0.15
    eing
    -0.14
    a
    -0.14
    eu
    -0.13
    evin
    -0.13
    equ
    -0.13
    aan
    -0.13
    ej
    -0.12
    ez
    -0.12
    POSITIVE LOGITS
    ola
    0.11
    izens
    0.10
    izen
    0.09
    storm
    0.09
    ply
    0.09
    uation
    0.08
    zer
    0.08
    aller
    0.08
    ernes
    0.08
    posting
    0.08
    Activations Density 0.007%

    No Known Activations