© 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. 28355
    Prev
    Next
    INDEX
    Explanations

    away movements

    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
     Alonso
    -0.10
    iese
    -0.10
     Ori
    -0.10
     Manufact
    -0.10
    875
    -0.09
     arp
    -0.09
     manufactured
    -0.09
    ipt
    -0.09
    ophobia
    -0.09
     ori
    -0.09
    POSITIVE LOGITS
     Sec
    0.10
     away
    0.10
    arda
    0.10
     onto
    0.10
     perman
    0.10
     Nicola
    0.09
     ephem
    0.09
    AndGet
    0.09
     off
    0.09
    Sec
    0.09
    Activations Density 0.018%

    No Known Activations