© 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. 50199
    Prev
    Next
    INDEX
    Explanations

    long story short

    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
     malt
    -0.11
     clearly
    -0.11
     Clearly
    -0.10
    marca
    -0.10
    Clearly
    -0.10
    aims
    -0.10
     cole
    -0.10
     playbook
    -0.10
    bonus
    -0.10
     unidentified
    -0.10
    POSITIVE LOGITS
     complicated
    0.29
     explain
    0.25
     explained
    0.24
     explanation
    0.23
     story
    0.23
     explanations
    0.23
     explains
    0.22
     explaining
    0.22
     Explanation
    0.21
     backstory
    0.19
    Activations Density 0.123%

    No Known Activations