© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90341
    Prev
    Next
    INDEX
    Explanations

    weblog, website, webinar

    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
     slee
    -0.09
    dob
    -0.08
     Voor
    -0.08
     sh
    -0.08
     webpage
    -0.08
     Shak
    -0.08
     stump
    -0.08
     av
    -0.08
     hail
    -0.08
    avl
    -0.07
    POSITIVE LOGITS
    inar
    0.15
    inars
    0.14
    aram
    0.12
    ARAM
    0.11
    Hold
    0.11
    masters
    0.10
     reserved
    0.10
     Holding
    0.10
    flow
    0.10
    /packages
    0.10
    Activations Density 0.050%

    No Known Activations