© 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. 32280
    Prev
    Next
    INDEX
    Explanations

    turned on or off

    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
     unp
    -0.10
    gli
    -0.09
    ington
    -0.09
     stuck
    -0.09
    OLON
    -0.09
    drs
    -0.08
     gn
    -0.08
    elp
    -0.08
    uner
    -0.08
    _medium
    -0.08
    POSITIVE LOGITS
     Down
    0.10
     hybrids
    0.10
     DOWN
    0.09
     @$
    0.09
    arra
    0.09
    вед
    0.09
     dup
    0.09
    Down
    0.09
     pri
    0.09
     mole
    0.09
    Activations Density 0.003%

    No Known Activations