© 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. 113678
    Prev
    Next
    INDEX
    Explanations

    and followed by noun

    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
     damn
    -0.07
     oft
    -0.06
     allegedly
    -0.06
     Humph
    -0.06
     Uhr
    -0.06
     thoroughly
    -0.06
     trag
    -0.06
     ones
    -0.06
    “.
    -0.06
     decidedly
    -0.06
    POSITIVE LOGITS
    CHASE
    0.14
    rog
    0.14
    rox
    0.13
    antar
    0.12
    roz
    0.12
    led
    0.12
    ä¸įèĥ½
    0.12
     WHATSOEVER
    0.12
    oland
    0.11
     TRACE
    0.11
    Activations Density 0.147%

    No Known Activations