© 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. 29281
    Prev
    Next
    INDEX
    Explanations

    multiple features and functionalities

    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
     smartphones
    -0.12
     instrumentation
    -0.12
     computers
    -0.12
     smartphone
    -0.12
     TVs
    -0.12
     toys
    -0.12
     shack
    -0.11
     laptops
    -0.11
     laptop
    -0.11
     desktop
    -0.11
    POSITIVE LOGITS
     backlight
    0.13
     battery
    0.12
     screen
    0.12
     dial
    0.11
     bez
    0.11
     scrolled
    0.11
     buttons
    0.11
     functionalities
    0.11
     Battery
    0.10
     scrolling
    0.10
    Activations Density 0.305%

    No Known Activations