© 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. 33660
    Prev
    Next
    INDEX
    Explanations

    description of events or people

    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
    Multiplicity
    -0.10
     cann
    -0.10
    angling
    -0.10
     注
    -0.09
     Cot
    -0.09
     unde
    -0.09
     uncomment
    -0.09
    eries
    -0.09
    .backend
    -0.09
     rooting
    -0.09
    POSITIVE LOGITS
     description
    0.60
     descriptions
    0.59
     describe
    0.47
     Description
    0.47
     describing
    0.45
    description
    0.44
     described
    0.42
     describes
    0.42
    -description
    0.41
     descri
    0.40
    Activations Density 0.457%

    No Known Activations