© 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. 5612
    Prev
    Next
    INDEX
    Explanations

    he + common endings

    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
    sterdam
    -0.09
    meer
    -0.08
    anos
    -0.08
    vern
    -0.07
    omi
    -0.07
    urs
    -0.07
    bridge
    -0.07
    ena
    -0.07
    men
    -0.07
    res
    -0.07
    POSITIVE LOGITS
    eding
    0.14
    arily
    0.13
    ying
    0.12
    eping
    0.12
    edback
    0.12
    iating
    0.12
    eded
    0.11
     heed
    0.11
    ğ
    0.11
    ening
    0.11
    Activations Density 0.014%

    No Known Activations