© 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. 25338
    Prev
    Next
    INDEX
    Explanations

    technical terms or file paths

    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
     rig
    -0.08
     Packs
    -0.08
     orchestr
    -0.08
     external
    -0.08
     Bench
    -0.08
     ext
    -0.07
    aille
    -0.07
     overseas
    -0.07
     Suff
    -0.07
     internal
    -0.07
    POSITIVE LOGITS
    sen
    0.11
     trousers
    0.11
    esen
    0.10
     Arist
    0.10
    oni
    0.10
    roe
    0.10
     Tits
    0.09
     Addiction
    0.09
    ús
    0.09
     denom
    0.09
    Activations Density 0.001%

    No Known Activations