© 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. 6943
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     Mare
    -0.09
     Pose
    -0.09
     foul
    -0.09
     Besch
    -0.08
     Clause
    -0.08
     Di
    -0.08
     businessmen
    -0.08
     fucks
    -0.08
     shit
    -0.08
     bog
    -0.08
    POSITIVE LOGITS
     condo
    0.11
     CHAPTER
    0.10
     Chall
    0.10
    ——
    0.10
     Cros
    0.10
     Bannon
    0.10
    orro
    0.10
     stealth
    0.10
    émon
    0.10
     Mormon
    0.10
    Activations Density 0.243%

    No Known Activations