© 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. 26298
    Prev
    Next
    INDEX
    Explanations

    image filenames with numbers and hyphens

    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
     Primitive
    -0.09
     primitive
    -0.08
    ot
    -0.07
     immortal
    -0.07
     Lies
    -0.07
     Gins
    -0.07
     swept
    -0.07
     poisonous
    -0.07
     hyp
    -0.07
    y
    -0.06
    POSITIVE LOGITS
    _Load
    0.11
     appendix
    0.11
     extras
    0.11
    JA
    0.11
    urator
    0.10
    isel
    0.10
    IDD
    0.10
     cach
    0.10
    Bookmark
    0.10
    dddd
    0.10
    Activations Density 0.039%

    No Known Activations