© 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. 89692
    Prev
    Next
    INDEX
    Explanations

    content release metadata

    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
    ">//
    -0.09
    bower
    -0.09
    .Companion
    -0.09
    notated
    -0.09
     Bair
    -0.09
     whirl
    -0.08
     defe
    -0.08
    _Syntax
    -0.08
     unin
    -0.08
    ionario
    -0.08
    POSITIVE LOGITS
    ToolStripMenuItem
    0.10
    Conexion
    0.09
    _outline
    0.09
    _note
    0.09
    /buttons
    0.09
    -Javadoc
    0.09
    _circle
    0.09
    _PF
    0.08
     AUX
    0.08
    _marshall
    0.08
    Activations Density 2.221%

    No Known Activations