© 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. 33297
    Prev
    Next
    INDEX
    Explanations

    a copy of the License

    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
    tas
    -0.10
    holm
    -0.10
    mos
    -0.10
    s
    -0.09
     unl
    -0.09
    orate
    -0.09
    sn
    -0.09
    SP
    -0.09
    VS
    -0.09
    rail
    -0.09
    POSITIVE LOGITS
    ustry
    0.11
    branches
    0.11
    iden
    0.11
    urther
    0.11
    uge
    0.11
    nder
    0.11
    kin
    0.11
    fx
    0.11
    db
    0.11
    ryan
    0.11
    Activations Density 0.001%

    No Known Activations