© 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. 88527
    Prev
    Next
    INDEX
    Explanations

    legal elements and status

    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
    inous
    -0.10
     chim
    -0.10
     Cannes
    -0.10
     dur
    -0.10
     Cann
    -0.09
    Brandon
    -0.09
    ilan
    -0.09
     branding
    -0.09
     packed
    -0.09
    acher
    -0.09
    POSITIVE LOGITS
    DBG
    0.10
    midd
    0.09
     Nel
    0.09
     gid
    0.09
    lac
    0.08
     DBG
    0.08
     racially
    0.08
    åħ¨éĥ¨
    0.08
    mez
    0.08
    rer
    0.08
    Activations Density 0.003%

    No Known Activations