© 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. 49880
    Prev
    Next
    INDEX
    Explanations

    import java

    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
     however
    -0.17
     meanwhile
    -0.14
     furthermore
    -0.14
     moreover
    -0.14
    however
    -0.13
     zwar
    -0.12
    unately
    -0.12
     meantime
    -0.10
     therefore
    -0.10
    alem
    -0.10
    POSITIVE LOGITS
    innen
    0.10
     Trom
    0.08
    illet
    0.08
     ~=
    0.07
    /current
    0.07
    edBy
    0.07
     Verfügung
    0.07
    [$_
    0.07
     #-
    0.07
     %.
    0.07
    Activations Density 5.430%

    No Known Activations