© 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. 90497
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
     Toast
    -0.08
     Gesture
    -0.08
    ane
    -0.08
    acks
    -0.08
     blas
    -0.08
     Ou
    -0.08
     outrageous
    -0.07
    /Product
    -0.07
    SON
    -0.07
    bara
    -0.07
    POSITIVE LOGITS
     subtype
    0.10
     gem
    0.10
     morally
    0.10
     Gem
    0.10
     hat
    0.09
    eature
    0.09
     undert
    0.09
    eko
    0.09
     meanwhile
    0.09
     Gain
    0.09
    Activations Density 0.088%

    No Known Activations