© 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. 90233
    Prev
    Next
    INDEX
    Explanations

    verbal comprehension and understanding

    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
    hay
    -0.10
    aines
    -0.09
    431
    -0.09
    horn
    -0.09
    /documentation
    -0.09
    allow
    -0.09
    ansen
    -0.09
    arat
    -0.08
    ottom
    -0.08
    /background
    -0.08
    POSITIVE LOGITS
     comprehend
    0.19
     concepts
    0.18
     understand
    0.18
     comprehension
    0.18
     grasp
    0.18
     vocabulary
    0.17
     basic
    0.17
     understands
    0.17
     understanding
    0.16
     language
    0.16
    Activations Density 0.269%

    No Known Activations