© 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. 114432
    Prev
    Next
    INDEX
    Explanations

    opinion issued

    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
     Morton
    -0.10
     depletion
    -0.09
    een
    -0.09
    itu
    -0.09
    leta
    -0.09
    inge
    -0.08
     deb
    -0.08
    temp
    -0.08
    yz
    -0.08
    ieu
    -0.08
    POSITIVE LOGITS
    ated
    0.22
    naire
    0.19
     polls
    0.16
     opinions
    0.15
     opinion
    0.13
    ATED
    0.13
    /views
    0.13
     expressed
    0.13
    /view
    0.13
     polling
    0.13
    Activations Density 0.051%

    No Known Activations