© 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. 49415
    Prev
    Next
    INDEX
    Explanations

    inspiring experiences and outcomes

    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
     lied
    -0.11
     Prev
    -0.11
     inh
    -0.11
     blindly
    -0.11
    535
    -0.11
     sach
    -0.10
     barr
    -0.10
    plies
    -0.10
     bund
    -0.10
    irie
    -0.10
    POSITIVE LOGITS
     inspire
    0.16
     inspired
    0.16
     inspiring
    0.15
     inspires
    0.15
     taught
    0.15
     cement
    0.13
     awaken
    0.13
     sparking
    0.13
     energ
    0.13
     reaff
    0.13
    Activations Density 0.209%

    No Known Activations