© 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. 4792
    Prev
    Next
    INDEX
    Explanations

    expressing opinion or view

    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
    ordin
    -0.11
     Marilyn
    -0.10
    evity
    -0.10
    eous
    -0.10
     Miguel
    -0.10
    Desk
    -0.09
    ymes
    -0.09
    inas
    -0.09
     Nim
    -0.09
     companions
    -0.09
    POSITIVE LOGITS
     opinion
    0.14
    /ex
    0.11
     Opinion
    0.10
    /app
    0.10
    HO
    0.09
     polls
    0.09
     Oper
    0.09
    iley
    0.09
     opinions
    0.08
     Pole
    0.08
    Activations Density 0.022%

    No Known Activations