© 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. 16544
    Prev
    Next
    INDEX
    Explanations

    dynamic

    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
     pride
    -0.10
     Shed
    -0.10
     tut
    -0.10
    dw
    -0.10
    venture
    -0.09
    ellas
    -0.09
    ataire
    -0.09
     Pride
    -0.09
     unconditional
    -0.09
    clc
    -0.09
    POSITIVE LOGITS
     duo
    0.15
    /static
    0.14
     Duo
    0.13
     range
    0.12
    _cast
    0.12
    (dynamic
    0.11
     dynamic
    0.11
    ially
    0.10
     Dynamic
    0.10
    oran
    0.10
    Activations Density 0.054%

    No Known Activations