© 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. 31431
    Prev
    Next
    INDEX
    Explanations

    convicted of a crime

    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
     repr
    -0.08
    writers
    -0.08
     xo
    -0.08
     Wyn
    -0.07
    omon
    -0.07
    BU
    -0.07
    elig
    -0.07
    layui
    -0.07
    newsletter
    -0.07
    nel
    -0.07
    POSITIVE LOGITS
    	this
    0.14
    these
    0.14
     this
    0.14
    this
    0.13
     THESE
    0.13
     these
    0.13
    .this
    0.12
    *this
    0.12
    -this
    0.12
    ,this
    0.12
    Activations Density 0.059%

    No Known Activations