© 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. 25541
    Prev
    Next
    INDEX
    Explanations

    neat description or action

    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
    host
    -0.09
     Buen
    -0.09
    hand
    -0.08
    isoft
    -0.08
     mixed
    -0.08
     loaded
    -0.08
    -loaded
    -0.08
    ASE
    -0.07
    hosts
    -0.07
     great
    -0.07
    POSITIVE LOGITS
     neatly
    0.20
    ness
    0.19
    liness
    0.16
     tidy
    0.15
    ened
    0.15
    -o
    0.15
     neat
    0.15
    (er
    0.14
     tucked
    0.14
     sever
    0.14
    Activations Density 0.023%

    No Known Activations