© 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. 88051
    Prev
    Next
    INDEX
    Explanations

    still active or remaining

    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
     STILL
    -0.12
     richer
    -0.11
     louder
    -0.10
    ren
    -0.10
    unlikely
    -0.10
    imu
    -0.10
    514
    -0.10
     redesigned
    -0.10
     simpler
    -0.10
    /docs
    -0.10
    POSITIVE LOGITS
     intact
    0.20
     alive
    0.16
     active
    0.14
     retains
    0.14
     retain
    0.13
    alive
    0.13
     faithful
    0.12
     lingering
    0.12
     retaining
    0.12
     viable
    0.12
    Activations Density 0.119%

    No Known Activations