© 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. 26021
    Prev
    Next
    INDEX
    Explanations

    documentation.LICENSE_1_0.txt

    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
     Howell
    -0.12
    obel
    -0.12
     Scarborough
    -0.11
     apar
    -0.10
    ippo
    -0.10
     Highlander
    -0.10
     CWE
    -0.10
     Bail
    -0.10
     fileInfo
    -0.10
     fertil
    -0.10
    POSITIVE LOGITS
     bust
    0.20
     Bust
    0.20
     Rust
    0.19
     Dust
    0.18
     rust
    0.17
     dust
    0.17
     Hust
    0.17
     Dustin
    0.16
     ust
    0.15
     Lust
    0.15
    Activations Density 0.423%

    No Known Activations