© 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. 89139
    Prev
    Next
    INDEX
    Explanations

    human experience and characteristics

    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
    world
    -0.09
    arp
    -0.09
     Derrick
    -0.08
     world
    -0.08
     Ordered
    -0.07
    708
    -0.07
     humans
    -0.07
     Effects
    -0.07
    /effects
    -0.07
    ced
    -0.07
    POSITIVE LOGITS
     adjunct
    0.11
    Ware
    0.11
     sexuality
    0.11
     POSSIBILITY
    0.11
     endeavor
    0.11
     Condition
    0.11
     interaction
    0.11
    ^(
    0.10
    RTC
    0.10
     condition
    0.10
    Activations Density 0.067%

    No Known Activations