© 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. 89625
    Prev
    Next
    INDEX
    Explanations

    range of words, help, ask

    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
     Towards
    -0.11
    owards
    -0.11
    Towards
    -0.10
     ie
    -0.10
     downwards
    -0.09
     Trevor
    -0.09
     alright
    -0.09
     regularization
    -0.09
     Gh
    -0.09
     neb
    -0.09
    POSITIVE LOGITS
     utilise
    0.19
     initialised
    0.18
     Initialise
    0.17
     initialise
    0.16
     util
    0.16
     personalised
    0.16
     realise
    0.16
     specialised
    0.15
     emphas
    0.14
     realised
    0.14
    Activations Density 0.643%

    No Known Activations