© 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. 14958
    Prev
    Next
    INDEX
    Explanations

    blogging, challenges, and linking

    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
     undermining
    -0.10
     Prototype
    -0.10
     undermine
    -0.10
     prototype
    -0.10
     dumb
    -0.09
     insider
    -0.09
     agency
    -0.09
     prototypes
    -0.09
     Kaplan
    -0.09
    prototype
    -0.09
    POSITIVE LOGITS
     bloggers
    0.21
     hosted
    0.18
     blogger
    0.17
     blogging
    0.17
     participating
    0.16
     hosts
    0.16
     linking
    0.15
     Blogger
    0.15
     link
    0.15
     links
    0.15
    Activations Density 0.448%

    No Known Activations