© 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. 16760
    Prev
    Next
    INDEX
    Explanations

    stock or sale information

    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
     Pil
    -0.12
     pil
    -0.10
     Lowell
    -0.09
     uncont
    -0.07
     Sag
    -0.07
    arsi
    -0.07
    enco
    -0.07
    weit
    -0.07
     Yours
    -0.07
    ivo
    -0.07
    POSITIVE LOGITS
    -board
    0.10
    ipe
    0.10
     GFX
    0.10
     Houses
    0.10
     crud
    0.10
     crim
    0.10
    +',
    0.09
     hailed
    0.09
    emente
    0.09
     Richardson
    0.09
    Activations Density 0.083%

    No Known Activations