© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89624
    Prev
    Next
    INDEX
    Explanations

    loss of value or control

    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
     disb
    -0.09
     fuller
    -0.08
     accidents
    -0.08
    Sr
    -0.08
     Loc
    -0.08
     Ari
    -0.08
     Fires
    -0.07
     meantime
    -0.07
    ire
    -0.07
     Full
    -0.07
    POSITIVE LOGITS
     valuable
    0.17
     dearly
    0.15
     control
    0.15
     privileges
    0.14
     credibility
    0.14
     access
    0.14
     everything
    0.13
     valued
    0.13
     precious
    0.13
     prive
    0.13
    Activations Density 0.037%

    No Known Activations