© 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. 32028
    Prev
    Next
    INDEX
    Explanations

    and then

    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
     :↵↵↵↵
    -0.11
     haz
    -0.11
    acer
    -0.11
    ohl
    -0.11
     crem
    -0.11
    -await
    -0.10
     preced
    -0.10
     volunte
    -0.10
    ],'
    -0.10
     arsch
    -0.10
    POSITIVE LOGITS
     therefore
    0.40
     thus
    0.31
     thereby
    0.30
     consequently
    0.29
     Therefore
    0.26
    Therefore
    0.26
     hence
    0.26
    thus
    0.25
     THAT
    0.23
     Thus
    0.21
    Activations Density 0.280%

    No Known Activations