© 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. 89466
    Prev
    Next
    INDEX
    Explanations

    I expressing opinion or preference

    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
    423
    -0.09
     shar
    -0.09
     penetr
    -0.09
     ded
    -0.08
    READ
    -0.08
     penetrating
    -0.08
     mitig
    -0.08
     tol
    -0.08
    hya
    -0.08
     equitable
    -0.08
    POSITIVE LOGITS
     recommend
    0.15
     recommending
    0.14
     affection
    0.12
     fav
    0.12
     fond
    0.12
     favor
    0.12
     recommends
    0.12
     favorites
    0.11
     favors
    0.11
     adore
    0.11
    Activations Density 0.441%

    No Known Activations