© 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. 88757
    Prev
    Next
    INDEX
    Explanations

    abstract:

    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
     Crate
    -0.11
     sexually
    -0.11
     collision
    -0.11
    DEX
    -0.11
    apper
    -0.11
     unpl
    -0.11
     spill
    -0.10
     Beard
    -0.10
     Reservation
    -0.10
     Gilles
    -0.10
    POSITIVE LOGITS
     opponent
    0.14
     tightening
    0.13
     opponents
    0.13
     tor
    0.12
     torque
    0.12
     tighten
    0.12
     pressure
    0.11
     tightened
    0.11
     tighter
    0.11
     tort
    0.11
    Activations Density 0.040%

    No Known Activations