© 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. 6669
    Prev
    Next
    INDEX
    Explanations

    requesting or offering help

    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
    Cancel
    -0.13
    imei
    -0.12
     aes
    -0.11
     dou
    -0.11
    ouden
    -0.11
    unker
    -0.11
    аÑĤоÑĢ
    -0.11
    tout
    -0.11
     FAR
    -0.11
    atts
    -0.10
    POSITIVE LOGITS
     oval
    0.09
     along
    0.09
    fully
    0.08
     spread
    0.08
     spreading
    0.08
     elong
    0.08
     enormously
    0.08
     ferry
    0.08
     indem
    0.08
     penetration
    0.08
    Activations Density 0.065%

    No Known Activations