© 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. 33816
    Prev
    Next
    INDEX
    Explanations

    GB patterns

    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
    assen
    -0.10
     ske
    -0.10
    ivate
    -0.09
     incom
    -0.09
    lope
    -0.08
    etro
    -0.08
     dsp
    -0.08
     proph
    -0.08
    idian
    -0.08
    нÑı
    -0.08
    POSITIVE LOGITS
     Bret
    0.11
     Pear
    0.10
     partition
    0.10
    arya
    0.09
    partition
    0.09
    inous
    0.09
    ages
    0.09
    iglia
    0.09
    /files
    0.09
    ROL
    0.09
    Activations Density 0.079%

    No Known Activations