© 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. 7710
    Prev
    Next
    INDEX
    Explanations

    Sort by

    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
    enco
    -0.12
     OP
    -0.11
    loy
    -0.10
    anel
    -0.10
    roi
    -0.10
    rome
    -0.10
     comp
    -0.10
     snork
    -0.10
    fade
    -0.10
     cat
    -0.10
    POSITIVE LOGITS
     unm
    0.07
     pref
    0.07
    criptor
    0.07
    “He
    0.07
    GR
    0.07
    ere
    0.06
     Cent
    0.06
    .beh
    0.06
     doubling
    0.06
    "He
    0.06
    Activations Density 0.046%

    No Known Activations