© 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. 50367
    Prev
    Next
    INDEX
    Explanations

    their respective

    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
    Their
    -0.18
     Their
    -0.17
    their
    -0.17
     their
    -0.15
     THEIR
    -0.15
     loro
    -0.15
    们
    -0.13
     leur
    -0.13
    They
    -0.13
     theirs
    -0.12
    POSITIVE LOGITS
    re
    0.12
     Pete
    0.09
    indi
    0.09
    r
    0.09
     ure
    0.08
    nette
    0.08
    UTE
    0.08
    DET
    0.08
    abl
    0.08
    icter
    0.08
    Activations Density 0.051%

    No Known Activations