© 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. 89006
    Prev
    Next
    INDEX
    Explanations

    abstract experiences and emotions

    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
     **/↵↵
    -0.10
    eric
    -0.10
      ↵↵
    -0.10
    lar
    -0.10
     duly
    -0.09
     PAR
    -0.09
     Vol
    -0.09
     Chamber
    -0.09
     dig
    -0.09
    vol
    -0.09
    POSITIVE LOGITS
    antom
    0.08
    zik
    0.08
    iot
    0.07
    Constructed
    0.07
    uchar
    0.07
     Cata
    0.07
     Blessed
    0.07
    mez
    0.07
     flavour
    0.07
     Curt
    0.07
    Activations Density 0.095%

    No Known Activations