© 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. 4665
    Prev
    Next
    INDEX
    Explanations

    reference citations for papers

    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
    hani
    -0.09
    antz
    -0.08
    NJ
    -0.08
     blunt
    -0.08
     trad
    -0.08
     innoc
    -0.08
     Chuck
    -0.08
     unt
    -0.08
    ku
    -0.07
    hp
    -0.07
    POSITIVE LOGITS
     enclosing
    0.11
    _relative
    0.10
    âĢIJ
    0.10
    ifa
    0.10
    igue
    0.10
     _(
    0.10
    rames
    0.10
     Dame
    0.09
     relative
    0.09
     Schul
    0.09
    Activations Density 0.005%

    No Known Activations