© 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. 33143
    Prev
    Next
    INDEX
    Explanations

    Third Kind

    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
     priv
    -0.08
    qd
    -0.08
     the
    -0.07
     Mast
    -0.07
     Bearing
    -0.07
    rsp
    -0.06
     spont
    -0.06
    ysize
    -0.06
     Eddie
    -0.06
    sic
    -0.06
    POSITIVE LOGITS
    :data
    0.11
    ?family
    0.11
    .UnitTesting
    0.11
    ipeg
    0.10
     Janeiro
    0.10
     Rica
    0.10
    byterian
    0.10
    orks
    0.10
     Krish
    0.10
     Rede
    0.10
    Activations Density 1.995%

    No Known Activations