© 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. 28155
    Prev
    Next
    INDEX
    Explanations

    social media and content platforms

    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
     Antoine
    -0.09
    bef
    -0.09
     autoc
    -0.08
     karma
    -0.08
    _msgs
    -0.08
     messaging
    -0.08
     msgs
    -0.08
     Meh
    -0.08
     links
    -0.08
     Autof
    -0.08
    POSITIVE LOGITS
    {text
    0.11
     sof
    0.11
    ãĥ»ãĥ»ãĥ»
    0.10
     inaug
    0.10
     null
    0.10
    blind
    0.10
     inde
    0.10
    undefined
    0.10
     foot
    0.10
     commemorate
    0.09
    Activations Density 0.009%

    No Known Activations