© 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. 48926
    Prev
    Next
    INDEX
    Explanations

    pouch

    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
    scribed
    -0.11
    sei
    -0.11
    linger
    -0.10
    orte
    -0.10
    ommen
    -0.10
    scri
    -0.10
    fits
    -0.10
    "go
    -0.10
     happiest
    -0.09
     Westbrook
    -0.09
    POSITIVE LOGITS
     deco
    0.09
    orro
    0.08
    es
    0.08
     intimate
    0.08
    /back
    0.08
    extract
    0.08
    mant
    0.08
    enum
    0.08
     brief
    0.07
    ing
    0.07
    Activations Density 0.003%

    No Known Activations