© 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. 15657
    Prev
    Next
    INDEX
    Explanations

    two

    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
    ?,?,?,?,
    -0.18
    ?,?,
    -0.13
     Five
    -0.10
     [[]
    -0.09
    äºĶ
    -0.09
    eree
    -0.09
    5
    -0.08
    seven
    -0.08
     ((((
    -0.08
    (Collections
    -0.08
    POSITIVE LOGITS
     two
    0.68
    两
    0.61
    two
    0.59
     Two
    0.55
    Two
    0.54
     TWO
    0.52
    _two
    0.49
    -two
    0.47
     duo
    0.47
     zwei
    0.45
    Activations Density 3.667%

    No Known Activations