© 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. 32244
    Prev
    Next
    INDEX
    Explanations

    treasure and treasury

    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
    ahan
    -0.11
    agher
    -0.09
    hon
    -0.09
    ament
    -0.09
    HING
    -0.09
    aled
    -0.09
     vd
    -0.08
    ars
    -0.08
    elter
    -0.08
    reason
    -0.08
    POSITIVE LOGITS
     tro
    0.19
     hunt
    0.15
     chests
    0.15
     hunter
    0.15
     hunters
    0.15
     treasure
    0.14
     chest
    0.13
    tro
    0.13
     hunts
    0.12
     hunting
    0.12
    Activations Density 0.008%

    No Known Activations