© 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. 4783
    Prev
    Next
    INDEX
    Explanations

    dates and attributions

    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
     HuffPost
    -0.13
    anst
    -0.11
     ENC
    -0.11
     corrupt
    -0.11
     IGN
    -0.11
     Huffington
    -0.10
    inkel
    -0.10
    ihan
    -0.10
    tiles
    -0.10
     punct
    -0.10
    POSITIVE LOGITS
    -overlay
    0.12
    Placeholder
    0.07
     canon
    0.07
    hin
    0.07
     inde
    0.07
     lak
    0.07
    alon
    0.07
     grass
    0.06
     unauthorized
    0.06
     finder
    0.06
    Activations Density 1.295%

    No Known Activations