© 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. 90961
    Prev
    Next
    INDEX
    Explanations

    plural roles and groups

    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
     preferably
    -0.10
    phe
    -0.10
     Oman
    -0.10
     Debugger
    -0.10
     preceded
    -0.09
     Omar
    -0.09
    iker
    -0.09
     sparking
    -0.09
     insignificant
    -0.09
    ikers
    -0.09
    POSITIVE LOGITS
     often
    0.20
    often
    0.15
     sometimes
    0.15
     feels
    0.14
     Often
    0.14
     frequently
    0.14
     resent
    0.14
     feel
    0.13
     need
    0.13
    Feel
    0.13
    Activations Density 0.177%

    No Known Activations