© 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. 28628
    Prev
    Next
    INDEX
    Explanations

    profile and related media

    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
     thrott
    -0.09
    upp
    -0.09
     handing
    -0.08
     Pru
    -0.08
     desks
    -0.08
    olin
    -0.07
     Manus
    -0.07
    065
    -0.07
    .help
    -0.07
     lug
    -0.07
    POSITIVE LOGITS
     biography
    0.16
     bio
    0.16
     profile
    0.15
     photos
    0.15
     Profile
    0.14
     pictures
    0.14
    (profile
    0.14
     Ratings
    0.13
     comments
    0.13
     photo
    0.13
    Activations Density 0.149%

    No Known Activations