© 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. 6374
    Prev
    Next
    INDEX
    Explanations

    dedicated sections

    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
     chim
    -0.11
     imm
    -0.10
    payload
    -0.10
    idot
    -0.10
     posible
    -0.09
    lee
    -0.09
    CAF
    -0.09
    ogy
    -0.09
    ichi
    -0.08
     ëĵ
    -0.08
    POSITIVE LOGITS
     dedicated
    0.42
     devoted
    0.35
     Dedicated
    0.33
     dedicate
    0.29
    ä¸ĵ
    0.25
     designated
    0.24
     dedic
    0.23
     reserved
    0.22
     specially
    0.21
     specifically
    0.19
    Activations Density 0.512%

    No Known Activations