© 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. 49446
    Prev
    Next
    INDEX
    Explanations

    producer, studio, collaborating

    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
     Reporting
    -0.13
    /service
    -0.12
     patrol
    -0.12
     Cipher
    -0.12
     patrols
    -0.11
    Reporting
    -0.11
    essen
    -0.11
     retali
    -0.11
     Posting
    -0.11
     deeds
    -0.11
    POSITIVE LOGITS
     producer
    0.19
     storyboard
    0.17
     studio
    0.16
     producers
    0.16
     Producer
    0.15
    Producer
    0.15
    studio
    0.14
     collaborating
    0.14
    producer
    0.14
     rehears
    0.14
    Activations Density 0.194%

    No Known Activations