© 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. 92131
    Prev
    Next
    INDEX
    Explanations

    knowledge and 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
     Spar
    -0.09
    atype
    -0.09
     foul
    -0.09
    Requirement
    -0.08
     Harris
    -0.08
    osal
    -0.08
     perk
    -0.08
    709
    -0.08
    dda
    -0.08
    arnation
    -0.08
    POSITIVE LOGITS
     tools
    0.36
     Tools
    0.26
    tools
    0.25
    -tools
    0.23
    Tools
    0.23
     confidence
    0.23
     toolkit
    0.22
     equip
    0.22
     knowledge
    0.21
     skills
    0.20
    Activations Density 0.474%

    No Known Activations