© 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. 15924
    Prev
    Next
    INDEX
    Explanations

    dead followed by pool or lock

    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
    arsi
    -0.08
    اس
    -0.08
     Laden
    -0.08
    iar
    -0.07
     vest
    -0.07
     expand
    -0.07
     Gad
    -0.07
    urally
    -0.07
     Rodgers
    -0.07
     iota
    -0.07
    POSITIVE LOGITS
    liest
    0.14
    lier
    0.14
    locked
    0.12
    ened
    0.11
    liness
    0.11
    pool
    0.11
    /live
    0.11
    beat
    0.11
    wood
    0.11
    rum
    0.11
    Activations Density 0.011%

    No Known Activations