© 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. 5742
    Prev
    Next
    INDEX
    Explanations

    Names followed by last names

    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
    Gain
    -0.09
    .NoSuch
    -0.09
     Gain
    -0.09
    &view
    -0.09
    afone
    -0.08
    gain
    -0.08
    .Utility
    -0.08
    _ENTER
    -0.08
     Kare
    -0.08
    .Compiler
    -0.08
    POSITIVE LOGITS
     hypoc
    0.10
     overd
    0.09
    .FileInputStream
    0.08
     Freddy
    0.08
    ember
    0.08
     strained
    0.08
     unin
    0.07
     pied
    0.07
    -fluid
    0.07
     explo
    0.07
    Activations Density 1.077%

    No Known Activations