© 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. 3831
    Prev
    Next
    INDEX
    Explanations

    self-identifies as

    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
     obs
    -0.10
     Dissertation
    -0.10
     div
    -0.09
     mounts
    -0.09
     dop
    -0.09
     equip
    -0.09
     imperson
    -0.09
    oler
    -0.09
     mounting
    -0.08
    (obs
    -0.08
    POSITIVE LOGITS
     labels
    0.19
     label
    0.19
     proudly
    0.18
     Labels
    0.17
     Label
    0.14
    Labels
    0.14
    label
    0.14
     proud
    0.14
    Label
    0.14
     Identity
    0.13
    Activations Density 0.116%

    No Known Activations