© 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. 27496
    Prev
    Next
    INDEX
    Explanations

    they tried/should/serve/got/can/might/are

    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
    èĩ
    -0.09
     Submitted
    -0.09
     personally
    -0.09
    ave
    -0.09
    FW
    -0.08
    avel
    -0.08
     independently
    -0.08
    eto
    -0.08
     FW
    -0.08
    .ft
    -0.08
    POSITIVE LOGITS
     televis
    0.11
     advertise
    0.11
     arresting
    0.11
     BRE
    0.10
    bre
    0.10
     filming
    0.10
     reprint
    0.10
     appoint
    0.10
    uta
    0.10
     announce
    0.10
    Activations Density 0.119%

    No Known Activations