© 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. 89915
    Prev
    Next
    INDEX
    Explanations

    colon followed by context

    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
     pur
    -0.12
     sponsors
    -0.09
     (@
    -0.09
    pur
    -0.09
    954
    -0.09
     sunset
    -0.09
    gan
    -0.09
     collection
    -0.09
    lint
    -0.08
     chron
    -0.08
    POSITIVE LOGITS
    Dick
    0.10
     gag
    0.10
     Virgin
    0.10
     anatom
    0.10
     Geld
    0.10
    dden
    0.10
     Dick
    0.09
     virt
    0.09
    illi
    0.09
    CAF
    0.09
    Activations Density 0.012%

    No Known Activations