© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15330
    Prev
    Next
    INDEX
    Explanations

    alarm clock, alarmists, alarm system

    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
    haar
    -0.13
    ying
    -0.09
    TING
    -0.09
    AKER
    -0.09
    jem
    -0.09
    mania
    -0.09
     laure
    -0.09
     apprec
    -0.09
    ê²
    -0.09
    lier
    -0.09
    POSITIVE LOGITS
    ingly
    0.25
     bells
    0.14
     clock
    0.13
     clocks
    0.13
     Clock
    0.12
    /alert
    0.11
    ingle
    0.11
    clock
    0.10
    ists
    0.10
    -clock
    0.10
    Activations Density 0.013%

    No Known Activations