© 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. 114866
    Prev
    Next
    INDEX
    Explanations

    slot machine, 30, 8

    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
     fatt
    -0.10
     preval
    -0.10
     [].
    -0.10
     Angels
    -0.10
    .Transform
    -0.09
    -dess
    -0.09
    ’.
    -0.09
    .poster
    -0.09
    Dod
    -0.09
     collectors
    -0.09
    POSITIVE LOGITS
     sporting
    0.09
     veg
    0.08
     spin
    0.08
     maths
    0.08
     Leia
    0.08
     neighbour
    0.08
     Runner
    0.08
     untrue
    0.08
     honour
    0.08
     thrust
    0.07
    Activations Density 0.002%

    No Known Activations