© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113304
    Prev
    Next
    INDEX
    Explanations

    and then

    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
     vra
    -0.09
    ves
    -0.09
    nos
    -0.09
    lop
    -0.08
    aga
    -0.08
     Meanwhile
    -0.08
     Cart
    -0.08
    cir
    -0.08
    obi
    -0.08
     ek
    -0.08
    POSITIVE LOGITS
     since
    0.15
     ours
    0.15
     fortunately
    0.15
     this
    0.15
     luckily
    0.14
     preferably
    0.14
     unfortunately
    0.13
    this
    0.13
     theirs
    0.13
    Since
    0.13
    Activations Density 0.125%

    No Known Activations