© 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. 6696
    Prev
    Next
    INDEX
    Explanations

    critical thinking skills

    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
    ised
    -0.10
    ized
    -0.10
    ated
    -0.09
    illi
    -0.09
     unfinished
    -0.08
    eded
    -0.08
    ATED
    -0.08
    itted
    -0.08
    homes
    -0.08
    trib
    -0.07
    POSITIVE LOGITS
     skills
    0.32
     abilities
    0.29
     capabilities
    0.27
    skills
    0.25
     Skills
    0.25
     capability
    0.24
     prowess
    0.22
     ability
    0.21
    Skills
    0.19
     Abilities
    0.19
    Activations Density 0.776%

    No Known Activations