© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 26925
    Prev
    Next
    INDEX
    Explanations

    here

    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
    PPP
    -0.09
     convention
    -0.08
    loff
    -0.08
     conventions
    -0.08
    Convention
    -0.08
    inidad
    -0.08
     PPP
    -0.08
    ova
    -0.08
    owo
    -0.08
     Canter
    -0.08
    POSITIVE LOGITS
     here
    0.49
    here
    0.35
     herein
    0.29
     Here
    0.28
     HERE
    0.28
    Here
    0.27
    _here
    0.26
     ici
    0.26
     aqui
    0.25
    HERE
    0.23
    Activations Density 0.094%

    No Known Activations