© 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. 5344
    Prev
    Next
    INDEX
    Explanations

    playful fun

    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
     Divider
    -0.10
     ÑĥÑģп
    -0.10
    -div
    -0.10
     grit
    -0.10
     Bust
    -0.09
     Eck
    -0.09
    actus
    -0.09
    esch
    -0.09
     escapes
    -0.09
     Shrine
    -0.09
    POSITIVE LOGITS
     fun
    0.35
     Fun
    0.25
    fun
    0.24
    Fun
    0.22
     FUN
    0.21
    .fun
    0.17
    _fun
    0.17
    (fun
    0.17
     tease
    0.16
     mischief
    0.16
    Activations Density 0.046%

    No Known Activations