© 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. 90905
    Prev
    Next
    INDEX
    Explanations

    explanation

    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
     vulnerable
    -0.12
     disadvantaged
    -0.11
     unfamiliar
    -0.11
    iny
    -0.11
     dus
    -0.10
     scratch
    -0.10
     insecure
    -0.10
     Scratch
    -0.10
     Without
    -0.10
    Without
    -0.10
    POSITIVE LOGITS
     protected
    0.14
     adrenaline
    0.13
     fortunately
    0.13
     aided
    0.13
     insulated
    0.13
     carefully
    0.13
     luckily
    0.12
     shelter
    0.12
     careful
    0.12
     buffered
    0.12
    Activations Density 0.484%

    No Known Activations