© 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. 29130
    Prev
    Next
    INDEX
    Explanations

    asking "why"

    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
     ener
    -0.10
     ready
    -0.08
     SF
    -0.08
     pag
    -0.08
    kin
    -0.08
     sui
    -0.08
    -ready
    -0.08
     stay
    -0.07
     stays
    -0.07
     Becker
    -0.07
    POSITIVE LOGITS
     Importance
    0.11
    wc
    0.10
    ocker
    0.10
     blurred
    0.10
    IRQ
    0.10
     Lionel
    0.10
    need
    0.10
    /use
    0.10
     nowhere
    0.10
    Howard
    0.10
    Activations Density 0.104%

    No Known Activations