© 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. 16045
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    s
    -0.33
    sand
    -0.15
    sar
    -0.14
    a
    -0.14
    l
    -0.13
    sburg
    -0.13
    scape
    -0.13
    sie
    -0.13
    sad
    -0.12
    sus
    -0.12
    POSITIVE LOGITS
    ↵
    0.13
    exemple
    0.11
    ника
    0.10
    ↵			↵
    0.10
    ulent
    0.10
    autiful
    0.09
     cuer
    0.09
    >čč↵
    0.09
    č↵
    0.09
    vel
    0.09
    Activations Density 0.071%

    No Known Activations