© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7937
    Prev
    Next
    INDEX
    Explanations

    detect, detached, detour, detectors, detroit

    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
    strand
    -0.12
    ctica
    -0.12
     incent
    -0.11
    forc
    -0.11
     encour
    -0.11
    icit
    -0.11
     vie
    -0.11
     Sau
    -0.10
    bast
    -0.10
     blatantly
    -0.10
    POSITIVE LOGITS
     Oswald
    0.09
     Detected
    0.09
    lov
    0.08
     bead
    0.08
     detected
    0.08
     hookup
    0.08
    eselect
    0.07
     Pru
    0.07
     mainstream
    0.07
    ieber
    0.07
    Activations Density 0.003%

    No Known Activations