© 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. 48947
    Prev
    Next
    INDEX
    Explanations

    voice over IP

    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
     gearing
    -0.08
     bankrupt
    -0.08
     respectable
    -0.08
    venue
    -0.08
     exh
    -0.08
    ôn
    -0.08
    ebb
    -0.08
    lash
    -0.08
     catering
    -0.08
     NSK
    -0.08
    POSITIVE LOGITS
     Codec
    0.11
     MB
    0.10
    .Remote
    0.10
     Clint
    0.10
    /fast
    0.10
     Reflex
    0.10
    orrent
    0.10
     Marty
    0.10
     distant
    0.10
    arlo
    0.09
    Activations Density 0.007%

    No Known Activations