© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6460
    Prev
    Next
    INDEX
    Explanations

    request to inform

    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
     contacting
    -0.12
     contacted
    -0.10
     interrogation
    -0.08
     deserving
    -0.08
    ssel
    -0.08
    -call
    -0.08
     messenger
    -0.08
    368
    -0.08
     calls
    -0.08
    isman
    -0.08
    POSITIVE LOGITS
     ask
    0.16
     inform
    0.14
     tell
    0.14
     arrang
    0.14
     warn
    0.13
     arrange
    0.13
    warn
    0.13
     inquire
    0.13
     asking
    0.12
     complain
    0.12
    Activations Density 0.104%

    No Known Activations