© 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. 114950
    Prev
    Next
    INDEX
    Explanations

    publish, report, any

    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
     recent
    -0.10
     lately
    -0.10
    ster
    -0.09
    akh
    -0.09
     really
    -0.09
     reliably
    -0.09
     plum
    -0.08
     yet
    -0.08
     notorious
    -0.08
    recent
    -0.08
    POSITIVE LOGITS
     any
    0.18
     reasonable
    0.17
    ANY
    0.15
     ANY
    0.15
    ä»»
    0.14
    shall
    0.13
    any
    0.13
     лÑİ
    0.13
    Any
    0.13
     shall
    0.12
    Activations Density 0.063%

    No Known Activations