© 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. 89835
    Prev
    Next
    INDEX
    Explanations

    not followed by verbs

    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
    ingly
    -0.10
    able
    -0.10
    uto
    -0.09
    craft
    -0.08
    UTO
    -0.08
    STITUTE
    -0.08
     spir
    -0.08
    Thumb
    -0.08
    adm
    -0.07
    halb
    -0.07
    POSITIVE LOGITS
    kus
    0.10
     nun
    0.10
     Unidos
    0.10
    ationally
    0.10
     Prelude
    0.10
    oble
    0.09
     Nun
    0.09
     segreg
    0.09
     NOT
    0.09
     Interrupt
    0.09
    Activations Density 0.022%

    No Known Activations