© 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. 28520
    Prev
    Next
    INDEX
    Explanations

    out of 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
    illes
    -0.11
     rever
    -0.09
     Tabs
    -0.09
    oso
    -0.09
    /reference
    -0.09
    ieties
    -0.08
     Hampton
    -0.08
    rlen
    -0.08
     stalk
    -0.08
     sparing
    -0.08
    POSITIVE LOGITS
     control
    0.52
     Control
    0.44
     uncont
    0.44
    control
    0.43
     controlled
    0.42
    -control
    0.40
    Control
    0.40
     CONTROL
    0.39
     controlling
    0.37
     controle
    0.37
    Activations Density 0.608%

    No Known Activations