© 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. 112938
    Prev
    Next
    INDEX
    Explanations

    not yet happened

    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
    imu
    -0.10
     Blond
    -0.09
    VS
    -0.09
    -cluster
    -0.09
    bane
    -0.08
     forever
    -0.08
     throughout
    -0.08
     Collector
    -0.08
    JA
    -0.08
     Forgotten
    -0.08
    POSITIVE LOGITS
     yet
    0.50
     haven
    0.44
     hasn
    0.43
    yet
    0.41
     hadn
    0.38
    haven
    0.37
     Haven
    0.36
     still
    0.32
    æľª
    0.32
     belum
    0.32
    Activations Density 0.789%

    No Known Activations