© 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. 26352
    Prev
    Next
    INDEX
    Explanations

    it's contraction

    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
    è¨
    -0.10
     Lux
    -0.09
     Sparks
    -0.09
     gör
    -0.08
    fits
    -0.08
     theirs
    -0.08
    JK
    -0.08
    isty
    -0.08
     exacerbated
    -0.08
     hers
    -0.08
    POSITIVE LOGITS
     complicated
    0.17
     tw
    0.12
     regarding
    0.11
    _complex
    0.11
     complex
    0.10
    Regarding
    0.10
     Regarding
    0.10
    simple
    0.10
     simpler
    0.10
     related
    0.10
    Activations Density 0.074%

    No Known Activations