© 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. 92187
    Prev
    Next
    INDEX
    Explanations

    stand out

    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
    IID
    -0.12
    ôt
    -0.12
     unl
    -0.11
     Bai
    -0.10
     Stra
    -0.10
    -common
    -0.10
     Eaton
    -0.10
     confuse
    -0.10
     unwilling
    -0.10
    IMS
    -0.10
    POSITIVE LOGITS
     special
    0.12
     standout
    0.10
     stand
    0.09
     so
    0.08
     apart
    0.08
    uya
    0.08
     fascinating
    0.08
     irresistible
    0.08
     exceptional
    0.08
     outstanding
    0.08
    Activations Density 0.003%

    No Known Activations