© 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. 27529
    Prev
    Next
    INDEX
    Explanations

    cover art or album art

    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
     complaint
    -0.10
    acam
    -0.10
    amework
    -0.10
     replay
    -0.10
     chant
    -0.09
     repl
    -0.09
    MLS
    -0.09
    afil
    -0.09
     stanza
    -0.09
    DOB
    -0.09
    POSITIVE LOGITS
     cover
    0.45
     Cover
    0.36
    cover
    0.35
     covers
    0.30
    -cover
    0.29
    Cover
    0.28
     COVER
    0.27
     poster
    0.26
     Covers
    0.26
    _cover
    0.25
    Activations Density 0.327%

    No Known Activations